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. 0-CLT-HP
    4. 40869
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
     of
    -0.74
     the
    -0.73
     
    -0.65
     Le
    -0.62
     in
    -0.60
     The
    -0.60
     per
    -0.60
     on
    -0.59
     an
    -0.58
     my
    -0.56
    POSITIVE LOGITS
    MigrationBuilder
    1.05
     Efq
    0.97
     Majefty
    0.96
    
    0.93
     ―――――
    0.92
     itſelf
    0.90
     Houſe
    0.87
     doubtnut
    0.86
     ་་
    0.85
     Cæsar
    0.82
    Activations Density 1.703%

    No Known Activations