Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74401
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
     Races
    -0.62
    enumii
    -0.59
     Infórmanos
    -0.58
     Signalez
    -0.56
     races
    -0.56
    Races
    -0.56
     razas
    -0.52
    races
    -0.49
    enumi
    -0.47
    #+#
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    1.04
     rep
    0.69
    MigrationBuilder
    0.68
    ẵn
    0.66
    Kaynakça
    0.66
     مؤرشف
    0.62
    مراجع
    0.59
    WriteLiteral
    0.59
     مشين
    0.58
    :✨
    0.58
    Activations Density 0.003%

    No Known Activations