© 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. 43959
    Prev
    Next
    INDEX
    Explanations

    named institutions

    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
    Cordialement
    -0.67
    HomeAsUpEnabled
    -0.66
    깥
    -0.66
     NACIONAL
    -0.63
    addPreferredGap
    -0.61
    jsonwebtoken
    -0.60
     surrounding
    -0.60
     therefore
    -0.59
     countries
    -0.59
     partly
    -0.59
    POSITIVE LOGITS
     anteriore
    0.45
     barnen
    0.45
     مواليد
    0.44
     numéros
    0.42
    displayquote
    0.42
     dieux
    0.41
     testigos
    0.41
     spectateurs
    0.41
    monary
    0.40
     Councilman
    0.40
    Activations Density 0.067%

    No Known Activations