© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1405
    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
    health
    -1.38
    Health
    -0.90
    HEALTH
    -0.88
     HEALTH
    -0.61
     health
    -0.61
    tymologie
    -0.60
    enapa
    -0.56
    DockStyle
    -0.56
    '])){
    -0.56
     Health
    -0.55
    POSITIVE LOGITS
    ier
    1.14
    iest
    1.05
    ian
    0.95
    s
    0.88
    ie
    0.80
    ies
    0.77
    iers
    0.77
    ians
    0.75
    ied
    0.73
    yers
    0.72
    Activations Density 1.548%

    No Known Activations