Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74321
    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
    PreExecute
    -0.59
     anzunehmen
    -0.58
    IndentedString
    -0.57
    calipsis
    -0.51
    __*/
    -0.51
    WithIdentifier
    -0.49
    Cheat
    -0.49
    ρχ
    -0.48
    InjectAttribute
    -0.47
    Mic
    -0.47
    POSITIVE LOGITS
     E
    0.64
     sta
    0.63
     e
    0.60
     Eco
    0.57
     ring
    0.52
     li
    0.51
     athlete
    0.50
     Ring
    0.50
    
    0.49
     Athlete
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.