© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 72036
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific content

    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
     فريبيس
    -0.83
    הערות
    -0.66
    BeginContext
    -0.65
     ویکی‌پدیا
    -0.63
    delwed
    -0.63
     ivelany
    -0.63
     autorytatywna
    -0.62
     NSCoder
    -0.62
    Pod
    -0.58
     Pod
    -0.56
    POSITIVE LOGITS
    olingo
    0.51
    leukin
    0.46
    turnstile
    0.45
     zra
    0.43
     Lawton
    0.43
     juridiques
    0.41
     закон
    0.40
    latan
    0.40
     makeStyles
    0.40
    vistas
    0.39
    Activations Density 0.001%

    No Known Activations