© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    Side-by-side compare needs a wider screen.
    Open other featureClose compare
    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `__str__` or `__init__` or `__type__`

    python-code · gemini-2.5-flash-lite

    max_ or __ine__ suffix (negative activations)

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    gest
    -0.07
    .he
    -0.07
    o
    -0.07
    own
    -0.06
    (he
    -0.06
     o
    -0.06
    oc
    -0.06
    essage
    -0.06
    ates
    -0.06
    od
    -0.05
    Positive Logits
    ()<|
    0.07
    timal
    0.07
    dint
    0.07
    straints
    0.07
    prese
    0.07
    "↵↵
    0.06
    }")↵↵
    0.06
    stac
    0.06
    didate
    0.06
    }")<|
    0.06
    Activations Density 100.000%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    dictionary unpacking or argument unpacking

    python-code · gemini-2.5-flash-lite

    set union operator (negative activations)

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Returns
    -0.10
    ")<|
    -0.07
    _matrix
    -0.06
    }")<|
    -0.05
    ()<|
    -0.05
     lat
    -0.05
    idual
    -0.05
    ú
    -0.05
    Á
    -0.05
    À
    -0.05
    Positive Logits
    __':↵
    0.08
     __
    0.08
    __(
    0.07
    __
    0.05
    __":↵
    0.05
    vai
    0.05
     tasks
    0.05
    ()
    0.05
    _tasks
    0.04
     task
    0.04
    Activations Density 100.000%

    No Known Activations