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. 74021
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
    complexContent
    -0.66
    ThroughAttribute
    -0.55
    nocache
    -0.50
     Poehler
    -0.45
    utilisons
    -0.43
    ANDUM
    -0.43
    MEMORANDUM
    -0.43
     UBC
    -0.43
    memoized
    -0.42
     CURIAM
    -0.42
    POSITIVE LOGITS
    antaranya
    0.69
     pitié
    0.64
    ufficio
    0.63
    Empereur
    0.62
    regard
    0.62
    Стоимость
    0.62
     présidenti
    0.61
     nôtre
    0.61
     relatifs
    0.61
     totalidad
    0.61
    Activations Density 0.004%

    No Known Activations