© 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. 1-CLT-HP
    7. 540
    Prev
    Next
    INDEX
    Explanations

    of

    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
     lèvres
    -0.70
     élus
    -0.63
     bébés
    -0.62
     malades
    -0.60
     frågan
    -0.59
     vœux
    -0.59
     fidèles
    -0.59
     jouets
    -0.57
     sociala
    -0.56
     bénévoles
    -0.56
    POSITIVE LOGITS
     times
    0.91
     occurrences
    0.65
    Autoritní
    0.60
    unknownFields
    0.59
     expected
    0.59
    (!__
    0.58
     required
    0.57
     <<<<<<<<<<<<<<
    0.57
     available
    0.56
     pages
    0.56
    Activations Density 0.015%

    No Known Activations