© 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. 1-CLT-HP
    7. 9341
    Prev
    Next
    INDEX
    Explanations

    virtual

    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
     coû
    -0.61
    virtual
    -0.61
    ROW
    -0.59
    Kjelder
    -0.57
     virtual
    -0.55
    patra
    -0.55
     découver
    -0.54
    ranton
    -0.54
     plufieurs
    -0.54
     organisée
    -0.53
    POSITIVE LOGITS
    gonic
    0.58
    RenderAtEndOf
    0.52
    록
    0.49
    pexpr
    0.46
     act
    0.46
     ballistic
    0.44
    BuilderFactory
    0.44
    tice
    0.44
    ossa
    0.43
    modelBuilder
    0.42
    Activations Density 0.127%

    No Known Activations