© 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. 45768
    Prev
    Next
    INDEX
    Explanations

    va

    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
    ScopeManager
    -0.71
    ConstraintMaker
    -0.56
    AnchorStyles
    -0.54
    Історія
    -0.53
    ftagPool
    -0.52
     批
    -0.51
     propOrder
    -0.51
     InputDecoration
    -0.51
    ThroughAttribute
    -0.51
     Bluffs
    -0.50
    POSITIVE LOGITS
    VersionUID
    0.62
    存于互联网档案馆
    0.57
    原始内容存档于
    0.55
    ⓧ
    0.49
    ideos
    0.48
    ρον
    0.47
    참고
    0.46
     Վերցված
    0.46
     bVar
    0.45
     Lerner
    0.44
    Activations Density 0.013%

    No Known Activations