© 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. 4-CLT-HP
    7. 3480
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     épaules
    -0.66
     seules
    -0.65
    MockBean
    -0.61
     genoux
    -0.61
     seuls
    -0.58
     gång
    -0.56
    RSpec
    -0.55
     móveis
    -0.55
     composizione
    -0.54
     peindre
    -0.54
    POSITIVE LOGITS
     greateſt
    0.66
     pleaſure
    0.65
     ſmall
    0.63
     perfons
    0.60
     Chriftian
    0.59
     occaf
    0.58
     ſche
    0.57
     fevere
    0.56
     ſta
    0.56
     lapis
    0.55
    Activations Density 0.029%

    No Known Activations