© 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. 1-CLT-HP
    7. 383
    Prev
    Next
    INDEX
    Explanations

    dermatology/medicine

    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
    Tembelea
    -0.74
    <bos>
    -0.69
    Билгалдахарш
    -0.59
    PostExecute
    -0.56
     lenker
    -0.56
    mor
    -0.52
    DataSnapshot
    -0.51
    DateTimeField
    -0.51
    ioutil
    -0.50
    errHandler
    -0.50
    POSITIVE LOGITS
     Anſ
    0.64
     pouvoit
    0.56
     démocr
    0.53
     Reſ
    0.53
     hâte
    0.50
    🏻‍♀️
    0.50
    heureux
    0.50
     betreft
    0.49
     feroit
    0.49
    abestanden
    0.49
    Activations Density 0.052%

    No Known Activations