© 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. 3349
    Prev
    Next
    INDEX
    Explanations

    health

    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
    .
    -0.62
     of
    -0.50
     pl
    -0.45
     like
    -0.45
     milieux
    -0.44
     for
    -0.43
     form
    -0.43
     or
    -0.42
     bit
    -0.42
     if
    -0.41
    POSITIVE LOGITS
     stället
    0.79
    CloseOperation
    0.76
    سطس
    0.76
    帖最后由
    0.75
    tagext
    0.74
    DockStyle
    0.74
    GEBURTSDATUM
    0.71
     ProtoMessage
    0.71
    COUVER
    0.70
    httphttps
    0.70
    Activations Density 0.009%

    No Known Activations