© 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. 0-CLT-HP
    7. 42964
    Prev
    Next
    INDEX
    Explanations

    one

    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
     délib
    -0.55
     mediodía
    -0.54
     enfans
    -0.51
     extérieurs
    -0.51
     satu
    -0.48
     one
    -0.48
    explique
    -0.48
     écrits
    -0.48
     constamment
    -0.48
    Pautan
    -0.47
    POSITIVE LOGITS
     of
    0.75
     للمعارف
    0.64
    tanleria
    0.63
    ThroughAttribute
    0.61
    ⋙
    0.59
     InputDecoration
    0.59
     end
    0.57
    joys
    0.57
    awtextra
    0.56
     spot
    0.54
    Activations Density 0.120%

    No Known Activations