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. 74138
    Prev
    Next
    INDEX
    Explanations

    Computer code/technical documentation

    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
     AssemblyTitle
    -0.64
     titolata
    -0.63
     ainfi
    -0.60
    ](#
    -0.59
     väga
    -0.56
     Italij
    -0.55
     zustand
    -0.54
     للاسماء
    -0.54
    WEBPACK
    -0.54
     étoit
    -0.54
    POSITIVE LOGITS
    IBarButtonItem
    0.60
    UnknownFieldSet
    0.60
     nakalista
    0.55
     that
    0.52
    ConverterFactory
    0.52
    sizeCache
    0.50
     side
    0.50
     cháy
    0.49
     symptom
    0.48
    NameInMap
    0.48
    Activations Density 0.003%

    No Known Activations