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. 74542
    Prev
    Next
    INDEX
    Explanations

    Technical language

    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
    FOR
    -1.02
    For
    -0.96
     For
    -0.82
     FOR
    -0.71
    for
    -0.61
    ForValue
    -0.61
     För
    -0.54
     Tại
    -0.54
     Für
    -0.54
    thâu
    -0.52
    POSITIVE LOGITS
    MemoryWarning
    0.63
    WriteBarrier
    0.58
    Portály
    0.58
     Spisak
    0.56
    ContentAlignment
    0.54
    enumii
    0.54
    })()
    0.54
     للاسماء
    0.53
    참고
    0.52
    
    0.52
    Activations Density 0.019%

    No Known Activations