© 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. 97517
    Prev
    Next
    INDEX
    Explanations

    Medical/technical terminology

    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
    urance
    -0.69
    hematical
    -0.65
     éte
    -0.63
     pitié
    -0.63
    adeloupe
    -0.63
     élas
    -0.63
     étoit
    -0.61
    fao
    -0.61
    riculture
    -0.60
    Wearing
    -0.59
    POSITIVE LOGITS
    s
    1.41
    ی
    0.80
    ing
    0.70
    ic
    0.69
    intios
    0.64
    ed
    0.63
    AndEndTag
    0.62
    san
    0.61
    sch
    0.60
    ים
    0.59
    Activations Density 1.609%

    No Known Activations