© 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. 14744
    Prev
    Next
    INDEX
    Explanations

    electrical

    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
    onAttach
    -0.61
     PPI
    -0.56
    fvar
    -0.54
     ARB
    -0.53
    endregion
    -0.52
     CRF
    -0.51
    MathML
    -0.50
    PhysRev
    -0.50
    IPR
    -0.49
    (!__
    -0.49
    POSITIVE LOGITS
    StoryboardSegue
    0.59
     للمعارف
    0.56
    ثيق
    0.51
    thodon
    0.50
    roidered
    0.49
     Cataloging
    0.48
    roscope
    0.47
     Normdatei
    0.47
     يتيمه
    0.47
    contentLoaded
    0.47
    Activations Density 0.026%

    No Known Activations