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. 1-CLT-HP
    4. 11172
    Prev
    Next
    INDEX
    Explanations

    Saul

    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
     Saul
    -1.76
    Saul
    -1.52
     saul
    -0.89
    aarrggbb
    -0.66
    TagHelper
    -0.65
     betweenstory
    -0.62
    WebElementEntity
    -0.55
    PropertyChanging
    -0.54
    argout
    -0.54
    InputLabel
    -0.53
    POSITIVE LOGITS
    rapie
    0.50
     breach
    0.49
     threat
    0.48
    úgó
    0.47
    Eloquent
    0.47
     gallop
    0.46
    zler
    0.45
    uvu
    0.45
    RenderAtEndOf
    0.45
     tess
    0.45
    Activations Density 0.008%

    No Known Activations