© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 821
    Prev
    Next
    INDEX
    Explanations

    end of common suffixes (negative activations)

    python-code · gemini-2.5-flash-lite

    license or environment

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    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
    Not in Any Lists

    No Comments

    Negative Logits
     nx
    -0.33
    ities
    -0.29
    ity
    -0.28
    ual
    -0.24
    oints
    -0.20
    ion
    -0.16
    cles
    -0.14
    gram
    -0.11
    ble
    -0.11
    tic
    -0.11
    POSITIVE LOGITS
    ip
    0.16
    lf
    0.14
    vers
    0.07
     dire
    0.07
    ard
    0.07
    .st
    0.04
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    Activations Density 100.000%

    No Known Activations