© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92417
    Prev
    Next
    INDEX
    Explanations

    newArrayList

    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
    UserScript
    -0.99
    ^(@)
    -0.97
     ویکی‌آمباردا
    -0.95
    SequentialGroup
    -0.94
     Référence
    -0.93
     мәкал
    -0.92
    nastics
    -0.90
    adays
    -0.89
    NUMX
    -0.89
    verständlich
    -0.89
    POSITIVE LOGITS
    <b>
    0.64
    http
    0.63
     morire
    0.57
    for
    0.56
    <i>
    0.56
    .
    0.54
     vaisselle
    0.52
    pla
    0.51
     exemplaires
    0.51
    A
    0.50
    Activations Density 0.161%

    No Known Activations