© 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. 0-CLT-HP
    7. 94853
    Prev
    Next
    INDEX
    Explanations

    energy

    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
     of
    -0.66
    الصفحه
    -0.50
     sayap
    -0.48
     DETERMINATION
    -0.48
    视
    -0.47
    enumi
    -0.47
    面
    -0.46
    več
    -0.45
     समीक्षाएं
    -0.45
    otype
    -0.45
    POSITIVE LOGITS
    __*/
    0.81
    GEBURTSDATUM
    0.71
    ьаж
    0.68
    forChild
    0.66
    ]]
    0.66
    setupUi
    0.65
     Pingback
    0.60
    MessageOf
    0.58
    ButterKnife
    0.58
     SIE
    0.57
    Activations Density 0.101%

    No Known Activations