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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73853
    Prev
    Next
    INDEX
    Explanations

    code/technical text

    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
    TagHelper
    -0.70
     définiti
    -0.67
     intérieure
    -0.67
     näky
    -0.65
     dépasser
    -0.65
    Бахар
    -0.63
     Italij
    -0.63
    WireFormatLite
    -0.62
     tiegħek
    -0.62
     profonde
    -0.61
    POSITIVE LOGITS
     m
    0.72
     ph
    0.59
     Im
    0.53
    AsUp
    0.50
    DoubleQuotes
    0.49
     im
    0.49
     <>",
    0.49
     M
    0.49
     Ph
    0.46
     cle
    0.46
    Activations Density 0.001%

    No Known Activations