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. 0-CLT-HP
    4. 40894
    Prev
    Next
    INDEX
    Explanations

    sarco

    np_max-act · 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
    asm
    -0.87
    ASM
    -0.73
     متعلقه
    -0.62
     spouse
    -0.56
    spouse
    -0.54
    
    -0.52
     península
    -0.52
    jön
    -0.50
    hesis
    -0.47
    correre
    -0.47
    POSITIVE LOGITS
    parsedMessage
    0.73
     itſelf
    0.66
    RuleContext
    0.63
    bootstrapcdn
    0.63
     raiſ
    0.63
     ſte
    0.60
     supp
    0.59
    évaluateur
    0.58
     whoſe
    0.58
    VIAF
    0.58
    Activations Density 0.097%

    No Known Activations