© 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. 0-CLT-HP
    7. 42159
    Prev
    Next
    INDEX
    Explanations

    Groups of people

    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
    \{\\
    -0.66
     فريبيس
    -0.59
    ValueStyle
    -0.54
    WEBPACK
    -0.53
     handleMessage
    -0.53
    arean
    -0.52
     males
    -0.52
     Adolescent
    -0.52
    ########.
    -0.51
    RepeatedField
    -0.51
    POSITIVE LOGITS
     merve
    0.57
    Hochspringen
    0.56
     समीक्षक
    0.52
     Grecs
    0.52
     générations
    0.49
     TAMBÉM
    0.49
    IVEREF
    0.47
     mukaan
    0.47
    يميديا
    0.47
     dieux
    0.46
    Activations Density 0.015%

    No Known Activations