© 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. 4-CLT-HP
    7. 4362
    Prev
    Next
    INDEX
    Explanations

    scientific/medical texts

    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
    openConnection
    -0.41
     +/-
    -0.39
     EdgeInsets
    -0.38
    writeFieldEnd
    -0.38
     dispu
    -0.38
     negotiable
    -0.38
     mechanically
    -0.37
     agreed
    -0.37
     InputDecoration
    -0.37
    uzzi
    -0.37
    POSITIVE LOGITS
    ſelf
    0.86
     poffible
    0.82
     ſtre
    0.79
     Jefus
    0.79
     ſeveral
    0.78
    neſs
    0.77
     itſelf
    0.77
     pleaſure
    0.75
    новниш
    0.72
     Anſ
    0.71
    Activations Density 0.029%

    No Known Activations