© 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. 9804
    Prev
    Next
    INDEX
    Explanations

    min

    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
    الحياه
    -0.66
    RegressionTest
    -0.54
    isan
    -0.49
     vapeur
    -0.49
    }:${
    -0.48
     bezeichneter
    -0.48
    }?
    -0.47
    RunWith
    -0.47
     déten
    -0.47
    RenderAtEndOf
    -0.47
    POSITIVE LOGITS
     juſt
    0.61
    agai
    0.57
     StatefulWidget
    0.57
    DrawerToggle
    0.55
     חיצוניים
    0.55
    ⓘ
    0.54
    ccb
    0.54
     τὰ
    0.54
     uſed
    0.54
    Ссылки
    0.53
    Activations Density 0.019%

    No Known Activations