© 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. 91129
    Prev
    Next
    INDEX
    Explanations

    countries

    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
     nation
    -0.96
     nations
    -0.87
     country
    -0.84
     national
    -0.84
     countries
    -0.79
     Nation
    -0.77
    national
    -0.74
    country
    -0.73
     Nations
    -0.69
    Country
    -0.68
    POSITIVE LOGITS
     EconPapers
    0.68
    ulemon
    0.66
    DockStyle
    0.63
    profen
    0.60
    interopRequire
    0.59
    parsedMessage
    0.59
     Legendre
    0.58
    ništ
    0.58
    رشف
    0.56
     Nectar
    0.56
    Activations Density 0.231%

    No Known Activations