© 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

    method call argument to .get

    python-code · gemini-2.5-flash-lite

    variable assignment (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
    his
    -0.03
     P
    -0.03
    P
    -0.02
     has
    -0.02
    p
    -0.01
     is
    -0.01
    hi
    -0.01
    ast
    -0.01
     it
    -0.01
     two
    -0.01
    Positive Logits
    ili
    0.07
    gle
    0.07
     enumerate
    0.07
    ility
    0.06
    ket
    0.06
    ilities
    0.06
    gor
    0.06
    ount
    0.06
    tions
    0.06
    ties
    0.06
    Activations Density 100.000%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `strength` variable attribute

    python-code · gemini-2.5-flash-lite

    `with open` context as (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
    pected
    -0.21
     base
    -0.13
    timal
    -0.09
    dint
    -0.09
    straints
    -0.08
    stac
    -0.07
    didate
    -0.07
     ValueError
    -0.07
    itial
    -0.07
     typing
    -0.06
    Positive Logits
    uild
    0.10
    uil
    0.08
    alc
    0.07
    old
    0.07
     build
    0.07
    new
    0.06
    ork
    0.05
    rue
    0.05
     Testing
    0.05
    (new
    0.05
    Activations Density 100.000%

    No Known Activations