© 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. 45122
    Prev
    Next
    INDEX
    Explanations

    have

    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
    miyorum
    -0.58
    tedt
    -0.50
     see
    -0.50
    来看看
    -0.50
     zien
    -0.50
    diğinde
    -0.49
    iyor
    -0.48
    ágok
    -0.47
    λισ
    -0.47
    看看
    -0.47
    POSITIVE LOGITS
    GraphicsUnit
    0.79
    ExecuteReader
    0.72
    jsxFileName
    0.71
    webElementXpaths
    0.68
     ProtoMessage
    0.67
    AutoScaleMode
    0.66
    StructEnd
    0.65
    expandindo
    0.64
    matchCondition
    0.63
    archiviato
    0.63
    Activations Density 1.587%

    No Known Activations