© 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. 42627
    Prev
    Next
    INDEX
    Explanations

    Without

    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
     ∼
    -0.70
    ymal
    -0.63
    движи
    -0.60
    カンド
    -0.60
    }-${
    -0.58
     springfox
    -0.57
    IMPORTED
    -0.57
    ().__
    -0.57
    DrawerToggle
    -0.57
    pherd
    -0.55
    POSITIVE LOGITS
    ArrowToggle
    0.64
    uxxxx
    0.59
     consultato
    0.58
    RenderAtEndOf
    0.56
     typelib
    0.52
     незавершена
    0.49
     GetEnumerator
    0.49
    neté
    0.48
    extAlignment
    0.48
     yyl
    0.46
    Activations Density 0.101%

    No Known Activations