© 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. 71471
    Prev
    Next
    INDEX
    Explanations

    code discussions

    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
    Negative Logits
    protoimpl
    -0.74
     متعلقه
    -0.74
     AssemblyTitle
    -0.73
    balleur
    -0.71
    +#+#
    -0.70
     ویکی‌پدی
    -0.69
    Personensuche
    -0.68
    mybatisplus
    -0.60
    wpdb
    -0.60
    InjectAttribute
    -0.59
    POSITIVE LOGITS
    */].
    0.47
    يران
    0.43
    AspNet
    0.42
    rét
    0.42
    onge
    0.41
    kier
    0.40
    gres
    0.40
    衬
    0.39
    kuuta
    0.39
    mustang
    0.39
    Activations Density 0.000%

    No Known Activations