© 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. 5-CLT-HP
    7. 1238
    Prev
    Next
    INDEX
    Explanations

    questions

    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
     ModelExpression
    -1.03
    AddTagHelper
    -0.78
     فريبيس
    -0.75
     why
    -0.72
     pourquoi
    -0.68
    Personendaten
    -0.68
     waarom
    -0.66
     preuves
    -0.65
     Warum
    -0.64
     Why
    -0.63
    POSITIVE LOGITS
     of
    0.92
     a
    0.60
    toObject
    0.54
     mView
    0.49
     an
    0.47
    handleRequest
    0.46
     our
    0.45
    newtheorem
    0.42
    Архівовано
    0.40
     someone
    0.40
    Activations Density 0.000%

    No Known Activations