© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44213
    Prev
    Next
    INDEX
    Explanations

    watts

    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
     habitually
    -0.88
     regularly
    -0.81
     myſelf
    -0.81
     routinely
    -0.80
     régulière
    -0.80
    protoc
    -0.79
     Efq
    -0.77
    endpush
    -0.75
     régulier
    -0.75
     regularity
    -0.74
    POSITIVE LOGITS
    ed
    0.56
    ised
    0.56
    ized
    0.45
    στ
    0.41
    Bism
    0.41
    </em>
    0.41
    es
    0.41
     nas
    0.40
    ige
    0.40
    </i>
    0.39
    Activations Density 0.034%

    No Known Activations