© 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. 38944
    Prev
    Next
    INDEX
    Explanations

    nerve

    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
     nerve
    -1.77
     Nerve
    -1.47
     permanent
    -1.20
     Permanent
    -1.07
    permanent
    -1.05
    Permanent
    -0.97
     permanente
    -0.88
     PERMAN
    -0.83
     permanentes
    -0.81
     permanently
    -0.73
    POSITIVE LOGITS
    انيف
    0.62
     }}}{
    0.60
     calendriers
    0.59
    ())).
    0.57
    ()]);
    0.57
     bond
    0.56
     endings
    0.55
    bete
    0.54
     gains
    0.53
    orderItem
    0.53
    Activations Density 0.204%

    No Known Activations