© 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. 0-CLT-HP
    7. 97639
    Prev
    Next
    INDEX
    Explanations

    medicine/drugs

    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
     distinguish
    -0.72
     selection
    -0.68
    y
    -0.66
    bug
    -0.59
     yat
    -0.59
    sse
    -0.57
     bug
    -0.57
     decomposition
    -0.57
    discrimination
    -0.56
     gainera
    -0.56
    POSITIVE LOGITS
    Personensuche
    0.85
    ngdoc
    0.83
     itſelf
    0.81
     purpoſe
    0.81
     myſelf
    0.80
     preſent
    0.78
    matchCondition
    0.75
     Anſ
    0.75
     transfieras
    0.71
    </caption>
    0.68
    Activations Density 0.423%

    No Known Activations