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. 40800
    Prev
    Next
    INDEX
    Explanations

    administrative divisions

    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
     society
    -1.55
    society
    -1.41
     SOCIETY
    -1.16
    Society
    -1.06
     Municipality
    -1.02
     ویکی‌پدی
    -1.02
     Majefty
    -1.02
     Society
    -1.02
     municipality
    -1.02
     myſelf
    -1.02
    POSITIVE LOGITS
    ,
    0.59
     S
    0.58
    .
    0.57
     Ar
    0.52
    /
    0.52
     R
    0.52
     in
    0.51
    e
    0.50
     war
    0.49
     A
    0.49
    Activations Density 0.263%

    No Known Activations