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. 20-CLT-HP
    4. 74047
    Prev
    Next
    INDEX
    Explanations

    Technical 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
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.79
     esternos
    -0.65
     to
    -0.64
     وتسجيلات
    -0.64
    ensement
    -0.64
     للمعارف
    -0.63
    setof
    -0.62
     élastique
    -0.58
     publicitaires
    -0.58
    WireFormatLite
    -0.56
    POSITIVE LOGITS
    дер
    0.45
     States
    0.45
     states
    0.45
    States
    0.44
     समीक्षाओं
    0.42
    back
    0.41
     covered
    0.40
     Mon
    0.39
     back
    0.39
     dis
    0.39
    Activations Density 0.000%

    No Known Activations