© 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. 10341
    Prev
    Next
    INDEX
    Explanations

    food inventories or diaries

    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
    Geplaatst
    -0.70
     estekak
    -0.60
     ujednoznacz
    -0.60
     MediatR
    -0.60
    Демографія
    -0.59
     상세
    -0.59
    Carriera
    -0.57
    rhosis
    -0.57
     ouvriers
    -0.57
     diaries
    -0.57
    POSITIVE LOGITS
     Wille
    0.44
    FormTagHelper
    0.44
     TAMBÉM
    0.43
    eur
    0.41
    andha
    0.39
    ItemBackground
    0.39
     wall
    0.39
     storage
    0.39
     Pty
    0.38
    感は
    0.38
    Activations Density 0.020%

    No Known Activations