© 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. 45561
    Prev
    Next
    INDEX
    Explanations

    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
    nologue
    -0.66
     Extragalactic
    -0.59
    eltzer
    -0.54
    Aves
    -0.54
     AssemblyCompany
    -0.52
    uarine
    -0.52
    OGND
    -0.49
    CrossRef
    -0.48
    axe
    -0.48
    horesis
    -0.47
    POSITIVE LOGITS
    ftc
    0.59
     بيها
    0.56
     فريبيس
    0.56
    სქოლიო
    0.54
    )))));
    0.53
    évaluateur
    0.53
     surla
    0.52
    expandindo
    0.52
     للمعارف
    0.51
    writeFieldEnd
    0.51
    Activations Density 0.057%

    No Known Activations