© 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. 1990
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical language

    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
    ua
    -0.52
     ple
    -0.46
    ям
    -0.45
     gu
    -0.44
     duras
    -0.44
    keits
    -0.43
     ä
    -0.43
    紀
    -0.43
    gu
    -0.43
    e
    -0.43
    POSITIVE LOGITS
    ніципалі
    0.87
    tagHelperRunner
    0.85
    DockStyle
    0.82
    SequentialGroup
    0.81
     itſelf
    0.76
     Meksiku
    0.75
     يتيمه
    0.73
    torta
    0.73
    Попис
    0.73
     myſelf
    0.73
    Activations Density 0.001%

    No Known Activations