© 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. 44173
    Prev
    Next
    INDEX
    Explanations

    Japan

    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
    Japan
    -0.81
     japan
    -0.77
     injection
    -0.73
     Japan
    -0.73
     EconPapers
    -0.71
    Invest
    -0.69
     Injection
    -0.68
     lolita
    -0.67
     Cæsar
    -0.65
     Japon
    -0.64
    POSITIVE LOGITS
    eses
    0.69
    es
    0.57
     disambiguazione
    0.57
    :
    0.56
    XmlAccessType
    0.56
    adpleegd
    0.54
    sidemargin
    0.54
    ">//
    0.53
    ,
    0.52
    ing
    0.51
    Activations Density 0.154%

    No Known Activations