© 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. 42206
    Prev
    Next
    INDEX
    Explanations

    orks

    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
    penup
    -0.57
    RenderAtEndOf
    -0.57
     Loos
    -0.57
     sinus
    -0.56
    ConstraintMaker
    -0.49
    Edm
    -0.43
    theoretical
    -0.41
    beti
    -0.39
    orks
    -0.39
     rijk
    -0.39
    POSITIVE LOGITS
     referenties
    0.70
    ppincott
    0.66
    ROIT
    0.65
     CHAPITRE
    0.64
     espagne
    0.63
     Oblivion
    0.63
    zzar
    0.63
    anyahu
    0.61
    edonia
    0.61
    ochemistry
    0.60
    Activations Density 0.130%

    No Known Activations