© 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. 4-CLT-HP
    7. 3418
    Prev
    Next
    INDEX
    Explanations

    Lady

    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
     مشين
    -0.52
    CppMethod
    -0.49
     intptr
    -0.48
    ImageContext
    -0.48
    providedIn
    -0.47
     unknownFields
    -0.45
    LElement
    -0.45
    titleMargin
    -0.44
     Jurist
    -0.42
    CppCodeGen
    -0.42
    POSITIVE LOGITS
     quæ
    0.77
     habet
    0.73
     ſen
    0.65
     quoque
    0.65
    ChildScrollView
    0.63
     eorum
    0.62
     ſur
    0.61
    Conduct
    0.60
    ícola
    0.60
     pyg
    0.60
    Activations Density 0.004%

    No Known Activations