© 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. 42822
    Prev
    Next
    INDEX
    Explanations

    Wo

    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
    RectangleBorder
    -0.66
     оригіналу
    -0.58
     potentials
    -0.57
    Wo
    -0.52
    inguish
    -0.52
     discipl
    -0.51
    reed
    -0.51
     Sist
    -0.51
    jsxFileName
    -0.51
     loop
    -0.49
    POSITIVE LOGITS
    ThroughAttribute
    0.66
    حياتها
    0.59
    NameInMap
    0.57
    phazard
    0.56
    ActionCreators
    0.55
    newswire
    0.55
    erover
    0.55
    ategy
    0.54
    //
    0.54
     Paglinawan
    0.54
    Activations Density 0.038%

    No Known Activations