© 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. 0-CLT-HP
    7. 44165
    Prev
    Next
    INDEX
    Explanations

    Medical/scientific terminology

    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
    tis
    -1.11
    BASELINE
    -0.75
    tvguidetime
    -0.72
    FT
    -0.71
    ft
    -0.71
    Tis
    -0.66
    клопе
    -0.65
    TIS
    -0.63
    fting
    -0.63
    fts
    -0.62
    POSITIVE LOGITS
     tartalmaz
    0.50
     Christendom
    0.49
    es
    0.48
     aukš
    0.47
    Tikang
    0.46
    Paying
    0.46
     originais
    0.45
     assistência
    0.44
     womanhood
    0.44
     vieill
    0.44
    Activations Density 0.080%

    No Known Activations