© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1217
    Prev
    Next
    INDEX
    Explanations

    looking

    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
    fromnode
    -0.69
     useSelector
    -0.59
    antuan
    -0.59
    anzen
    -0.57
    ndata
    -0.57
     choosing
    -0.57
     Accounts
    -0.56
    ütter
    -0.56
    ArgsConstructor
    -0.55
    anus
    -0.55
    POSITIVE LOGITS
     Paglinawan
    0.72
     for
    0.52
    Enders
    0.48
    PreferredItem
    0.46
    httphttps
    0.46
     ویکی‌پدیای
    0.44
    ourable
    0.44
     appelez
    0.44
     tillbaka
    0.43
    出版年
    0.43
    Activations Density 0.004%

    No Known Activations