© 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. 20-CLT-HP
    7. 72314
    Prev
    Next
    INDEX
    Explanations

    Spreadsheets and Excel

    np_max-act-logits · 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
    karte
    -0.56
    maty
    -0.56
    بوابة
    -0.54
    forName
    -0.50
    card
    -0.50
    jsdelivr
    -0.50
     tarjeta
    -0.49
     ivelany
    -0.49
     समीक्षक
    -0.49
    gemeen
    -0.48
    POSITIVE LOGITS
     Spread
    0.91
     spread
    0.85
    spread
    0.84
    Spread
    0.81
    IntoConstraints
    0.69
    DockStyle
    0.68
     pivot
    0.65
     surla
    0.64
     spreads
    0.64
    pread
    0.60
    Activations Density 0.004%

    No Known Activations