© 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. 45104
    Prev
    Next
    INDEX
    Explanations

    reactive

    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
     reactive
    -1.24
     mon
    -1.23
     Reactive
    -1.15
    mybatisplus
    -1.11
    Reactive
    -1.05
    reactive
    -1.00
    mon
    -0.97
    Mon
    -0.90
     Mon
    -0.82
    MON
    -0.80
    POSITIVE LOGITS
     flèche
    0.64
     šķ
    0.54
     sähkö
    0.53
     économie
    0.49
     vägen
    0.49
     gräns
    0.49
     :)</
    0.48
     poudre
    0.47
     meurt
    0.46
    -->
    0.46
    Activations Density 0.086%

    No Known Activations