© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10832
    Prev
    Next
    INDEX
    Explanations

    cuisine or seatbelts

    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
    InstrumentedTest
    -0.54
    __*/
    -0.50
     Италијани
    -0.48
    cono
    -0.47
     cuisine
    -0.45
    umumkan
    -0.44
    Abp
    -0.44
     aDecoder
    -0.44
    aroa
    -0.44
    город
    -0.43
    POSITIVE LOGITS
    SuppressLint
    0.66
     RISERVATA
    0.63
    RenderAtEndOf
    0.60
    TagHelpers
    0.56
     Femmes
    0.55
    ագրություններ
    0.53
     transmembrane
    0.52
     Unavailable
    0.51
     Cubans
    0.51
     masses
    0.50
    Activations Density 0.012%

    No Known Activations