© 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. 43255
    Prev
    Next
    INDEX
    Explanations

    text excerpts

    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
    i
    -0.76
    a
    -0.76
    s
    -0.72
    t
    -0.65
    d
    -0.64
     betweenstory
    -0.64
     AssemblyCulture
    -0.63
    e
    -0.63
     propOrder
    -0.60
    ArgsConstructor
    -0.59
    POSITIVE LOGITS
     inconvénients
    0.57
     élevées
    0.57
     gjen
    0.56
     gambe
    0.54
     élas
    0.54
     kèo
    0.53
     sconto
    0.53
     élevée
    0.52
     stället
    0.52
    bren
    0.52
    Activations Density 0.028%

    No Known Activations