© 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. 9786
    Prev
    Next
    INDEX
    Explanations

    world/universe

    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
    ViewInit
    -0.54
     world
    -0.49
    world
    -0.42
    WORLD
    -0.42
     Welt
    -0.41
     WORLD
    -0.40
    arino
    -0.40
    argas
    -0.40
    ardan
    -0.39
    PageIndex
    -0.39
    POSITIVE LOGITS
    ValueStyle
    0.79
    Personensuche
    0.75
    HasBeenSet
    0.68
    ArgsConstructor
    0.67
    RectangleBorder
    0.66
     ModelExpression
    0.65
    building
    0.63
    SharedDtor
    0.63
    ształ
    0.63
     rumahnya
    0.62
    Activations Density 0.026%

    No Known Activations