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. 74114
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     the
    -0.60
    ↵↵
    -0.57
    ,
    -0.56
     in
    -0.55
     all
    -0.54
    ↵
    -0.54
    ca
    -0.53
    p
    -0.53
    G
    -0.52
    te
    -0.52
    POSITIVE LOGITS
     Efq
    0.99
     becauſe
    0.97
     pleaſure
    0.94
    AddTagHelper
    0.93
     Majefty
    0.92
    ^(@)
    0.89
     Monfieur
    0.89
     itſelf
    0.88
     للمعارف
    0.86
     Theſe
    0.86
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.