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. 40843
    Prev
    Next
    INDEX
    Explanations

    istas

    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
     fifth
    -0.78
     sixth
    -0.71
     eighth
    -0.68
     seventh
    -0.67
     fourth
    -0.62
     ninth
    -0.61
    umed
    -0.60
    lav
    -0.60
     quinta
    -0.59
     cinquième
    -0.57
    POSITIVE LOGITS
    kháu
    0.62
    oO
    0.60
    ympto
    0.59
    protoimpl
    0.58
    出版年
    0.57
     Balik
    0.57
     Chaldean
    0.56
     deme
    0.56
    queous
    0.56
    ActionCreators
    0.56
    Activations Density 0.287%

    No Known Activations