© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5291
    Prev
    Next
    INDEX
    Explanations

    qualifications/exceptions

    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
    icordia
    -0.59
    calientes
    -0.54
     Projektu
    -0.53
     Vichy
    -0.52
     pleaſure
    -0.51
     кӀ
    -0.49
    foglio
    -0.49
    digung
    -0.49
     kcal
    -0.49
    ofar
    -0.47
    POSITIVE LOGITS
    rungsseite
    0.81
    RenderAtEndOf
    0.72
    LookAnd
    0.68
     &___
    0.66
    سياسي
    0.59
     MainAxisSize
    0.58
    ScopeManager
    0.56
    LayoutStyle
    0.55
     Erişim
    0.54
    AccessorTable
    0.54
    Activations Density 0.017%

    No Known Activations