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. 74340
    Prev
    Next
    INDEX
    Explanations

    Code-related terms

    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
    8
    -0.77
     eighth
    -0.68
     eight
    -0.63
     delapan
    -0.63
     متعلقه
    -0.59
    семь
    -0.57
    9
    -0.57
    8
    -0.56
     Eight
    -0.55
    八
    -0.55
    POSITIVE LOGITS
    Portail
    0.85
    IANGLES
    0.75
     ExecuteAsync
    0.73
    providedIn
    0.68
     resourceCulture
    0.67
    \{\\
    0.66
    Datuak
    0.66
    !*\
    0.62
    AnchorStyles
    0.61
    CloseOperation
    0.61
    Activations Density 0.002%

    No Known Activations