© 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. 4326
    Prev
    Next
    INDEX
    Explanations

    adverbs of degree

    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
     significant
    -0.71
     changed
    -0.63
     increased
    -0.62
     changeable
    -0.57
     increasing
    -0.57
    DispatchToProps
    -0.57
    блица
    -0.57
     impressive
    -0.56
     distinctive
    -0.56
     flexible
    -0.56
    POSITIVE LOGITS
    exitRule
    0.66
     generazione
    0.57
     dopiero
    0.57
     with
    0.56
    .
    0.52
     scaricare
    0.52
     înc
    0.52
     because
    0.51
     pasada
    0.50
     during
    0.49
    Activations Density 0.003%

    No Known Activations