© 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

    `__init__` method definition

    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
     q
    -0.09
    q
    -0.07
    22
    -0.05
    gs
    -0.04
     r
    -0.04
    .d
    -0.04
    Q
    -0.04
     id
    -0.03
     dist
    -0.03
    X
    -0.02
    Positive Logits
    ffe
    0.06
    imum
    0.05
    adjac
    0.04
    li
    0.03
     spe
    0.03
    ing
    0.02
    and
    0.02
     co
    0.01
        ↵
    0.01
    S
    0.01
    Activations Density 51.818%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list comprehension closing bracket (negative activations)

    python-code · gemini-2.5-flash-lite

    numbers after 'str',

    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
    ;
    -0.03
    ][
    -0.02
    ,↵
    -0.02
     #
    -0.02
    :",
    -0.02
    ,
    -0.02
     for
    -0.02
    :
    -0.02
    ):
    -0.02
     ->
    -0.01
    Positive Logits
    .random
    0.02
    |>
    0.02
    ↵        ↵
    0.02
    ↵
    0.02
    ↵↵
    0.01
    ↵    ↵
    0.01
     enumerate
    0.01
    ↵            ↵
    0.01
    [:
    0.01
    č
    0.01
    Activations Density 60.590%

    No Known Activations