© 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

    for loop body

    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
    ()
    -0.06
    0
    -0.04
    ")
    -0.04
     path
    -0.03
    ')
    -0.03
     shortest
    -0.03
    timal
    -0.03
    losest
    -0.03
    º
    -0.03
    _path
    -0.03
    Positive Logits
    ice
    0.05
    ise
    0.05
    ł
    0.04
    ir
    0.04
    isi
    0.04
     L
    0.03
    i
    0.03
    vai
    0.03
    ),↵
    0.03
    index
    0.03
    Activations Density 58.256%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    dot followed by identifier

    python-code · gemini-2.5-flash-lite

    digits followed by comma or colon (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
    rt
    -0.05
    _of
    -0.04
    _to
    -0.03
    ct
    -0.02
    lay
    -0.02
    ut
    -0.01
    X
    -0.01
     This
    -0.01
    r
    -0.01
    k
    -0.01
    Positive Logits
     start
    0.02
     source
    0.01
    start
    0.01
    .start
    0.01
    tail
    0.01
     root
    0.01
    form
    0.01
    80
    0.01
    de
    0.01
    le
    0.01
    Activations Density 73.070%

    No Known Activations