© 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. 5-CLT-HP
    7. 2059
    Prev
    Next
    INDEX
    Explanations

    medal

    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
    mtrl
    -0.65
     medals
    -0.53
     medal
    -0.53
    CloseOperation
    -0.52
    LLocation
    -0.51
    Metals
    -0.50
    argout
    -0.49
    ">//
    -0.48
     Metals
    -0.48
    Brainz
    -0.48
    POSITIVE LOGITS
     ModelExpression
    0.65
    Parcelize
    0.60
    adaptiveStyles
    0.52
     TextInputType
    0.51
     Kanpur
    0.50
    arschijnlijk
    0.50
    makeConstraints
    0.49
     moeite
    0.49
     myſelf
    0.49
    енча
    0.48
    Activations Density 0.018%

    No Known Activations