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. 40893
    Prev
    Next
    INDEX
    Explanations

    import

    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
     source
    -0.92
     sources
    -0.90
    source
    -0.74
    sources
    -0.71
     Sources
    -0.69
     SOURCES
    -0.60
     import
    -0.59
     Quellen
    -0.57
     sumber
    -0.56
    SOURCES
    -0.56
    POSITIVE LOGITS
    protoimpl
    0.90
     Efq
    0.82
    ();)
    0.77
    ']))
    
    0.71
     colic
    0.71
     himo
    0.70
     sumpay
    0.67
    StructEnd
    0.67
     itſelf
    0.67
    ')));
    0.66
    Activations Density 0.218%

    No Known Activations