© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9087
    Prev
    Next
    INDEX
    Explanations

    council

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     council
    -1.59
    Council
    -1.50
     Council
    -1.48
    council
    -1.38
     COUNCIL
    -1.34
     councils
    -1.27
     Councils
    -1.12
    ouncil
    -0.82
    UNCIL
    -0.76
     Coun
    -0.73
    POSITIVE LOGITS
     CURIAM
    1.04
    DockStyle
    1.00
    parsedMessage
    0.94
    EndGlobalSection
    0.88
     nahilalakip
    0.85
     kasarigan
    0.85
     defaultstate
    0.85
     Roskov
    0.83
     transfieras
    0.83
     AssemblyCulture
    0.82
    Activations Density 0.096%

    No Known Activations