© 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. 97206
    Prev
    Next
    INDEX
    Explanations

    morphine

    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
     morphine
    -1.63
     виправивши
    -0.80
    ➟
    -0.79
    цездатний
    -0.74
    expandindo
    -0.73
     NSCoder
    -0.72
     disambiguazione
    -0.70
    aarrggbb
    -0.70
    ThroughAttribute
    -0.68
    :✨
    -0.68
    POSITIVE LOGITS
    AttributeSet
    0.59
    Mvc
    0.55
     Body
    0.54
    Body
    0.51
    set
    0.50
    tich
    0.50
    err
    0.49
    bez
    0.49
    Model
    0.49
    ko
    0.48
    Activations Density 0.571%

    No Known Activations