© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71578
    Prev
    Next
    INDEX
    Explanations

    during

    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
    uxxxx
    -1.06
    脚注の使い方
    -1.04
     ModelExpression
    -1.03
    Autoritní
    -1.01
     kaarangay
    -0.99
     تضيفلها
    -0.98
     ویکی‌پدی
    -0.95
    UrlResolution
    -0.93
     فريبيس
    -0.91
    Abitanti
    -0.90
    POSITIVE LOGITS
     Week
    0.58
     week
    0.47
     the
    0.46
    Week
    0.44
     both
    0.43
     either
    0.41
     Wave
    0.41
     Year
    0.40
     all
    0.39
    定
    0.38
    Activations Density 0.001%

    No Known Activations