© 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

    `print(` or `def` or `)` (negative activations)

    python-code · gemini-2.5-flash-lite

    string.ascii

    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
    .random
    -0.05
     {}↵↵
    -0.03
     {}↵
    -0.02
     []↵↵
    -0.02
     collections
    -0.02
    [
    -0.02
     []↵
    -0.02
     typing
    -0.01
     parse
    -0.01
    }↵↵
    -0.01
    Positive Logits
     "
    0.05
     '
    0.04
    .append
    0.02
    !
    0.01
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    )
    0.00
    Activations Density 68.642%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    method call `peek` or `writer`

    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
    tic
    -0.03
    .heapp
    -0.02
    xb
    -0.02
    xc
    -0.02
    xf
    -0.02
    xd
    -0.02
    xe
    -0.02
    place
    -0.02
    gram
    -0.02
    £
    -0.02
    Positive Logits
    K
    0.06
    Å
    0.05
     if
    0.05
    ke
    0.04
     weights
    0.04
    Ä
    0.04
    ok
    0.04
    _key
    0.04
     while
    0.04
    keys
    0.04
    Activations Density 23.145%

    No Known Activations