© 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. 9711
    Prev
    Next
    INDEX
    Explanations

    why

    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
     sánchez
    -0.65
     Hift
    -0.61
     Majefty
    -0.60
     fernández
    -0.60
     Jefus
    -0.59
    weichen
    -0.59
    ksesta
    -0.58
     elector
    -0.57
    hdessä
    -0.57
     preſent
    -0.56
    POSITIVE LOGITS
    BeginContext
    0.59
     resourceCulture
    0.53
    RenderAtEndOf
    0.52
    <?
    0.50
    reportWebVitals
    0.47
    ❋
    0.47
    typeparam
    0.47
    Lähteet
    0.46
    feeds
    0.46
     فريبيس
    0.45
    Activations Density 0.020%

    No Known Activations