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. 74586
    Prev
    Next
    INDEX
    Explanations

    technical reviews

    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
    sizeCache
    -0.58
    gensen
    -0.52
     propOrder
    -0.48
     архивлан
    -0.47
    Попис
    -0.47
    jspx
    -0.44
    complexContent
    -0.44
    fjspx
    -0.43
    GeneratedCode
    -0.43
    IMDG
    -0.42
    POSITIVE LOGITS
     epist
    0.63
    DoubleQuotes
    0.59
     anhyd
    0.59
    ympto
    0.57
     Provisional
    0.56
    haja
    0.55
    ynchronously
    0.55
    baller
    0.55
     الاطلاع
    0.53
    hirts
    0.53
    Activations Density 0.009%

    No Known Activations