© 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. 2192
    Prev
    Next
    INDEX
    Explanations

    medical context

    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
     BoxDecoration
    -0.73
    
    -0.60
    faatkan
    -0.60
    runApp
    -0.59
     FetchType
    -0.59
    EditorGUILayout
    -0.58
    Gemeinsame
    -0.56
    олові
    -0.55
    `{.
    -0.55
    צלחה
    -0.55
    POSITIVE LOGITS
     episodes
    0.50
     Zentrum
    0.47
    pannt
    0.46
     heart
    0.46
    ynb
    0.46
    lossene
    0.45
    ,
    0.44
     Pohl
    0.44
    zag
    0.43
     Guevara
    0.43
    Activations Density 0.000%

    No Known Activations