© 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. 0-CLT-HP
    7. 43387
    Prev
    Next
    INDEX
    Explanations

    lead

    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
     leading
    -2.06
    leading
    -1.88
     Leading
    -1.69
    Leading
    -1.66
     leads
    -1.22
     füh
    -1.15
     menant
    -0.95
     Leads
    -0.91
    leads
    -0.88
    LEADING
    -0.87
    POSITIVE LOGITS
     Normdatei
    0.78
    MessageOf
    0.76
    twimg
    0.65
    BagConstraints
    0.61
    __*/
    0.61
    aarrggbb
    0.60
    IMPORTED
    0.58
     Lons
    0.57
    migrationBuilder
    0.56
    ctid
    0.56
    Activations Density 0.574%

    No Known Activations