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. 1-CLT-HP
    4. 12935
    Prev
    Next
    INDEX
    Explanations

    College sports and universities

    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
    <bos>
    -0.61
     šķ
    -0.49
     of
    -0.48
     citoy
    -0.48
     particularly
    -0.47
     répondit
    -0.46
     skjø
    -0.45
     that
    -0.43
    šanai
    -0.43
    praš
    -0.42
    POSITIVE LOGITS
    ftagPool
    0.97
    ItemBackground
    0.92
     AssemblyCulture
    0.83
    Hentet
    0.78
    GEBURTSDATUM
    0.77
     चीज़ों
    0.74
     виправивши
    0.74
    ctibles
    0.67
     ISNI
    0.66
     disambiguazione
    0.66
    Activations Density 0.051%

    No Known Activations