© 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. 15682
    Prev
    Next
    INDEX
    Explanations

    have

    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
     ArrayAdapter
    -0.72
     espirituales
    -0.67
     للمعارف
    -0.63
     bénévoles
    -0.62
     métallique
    -0.61
     لينك
    -0.60
     militaires
    -0.60
    casila
    -0.60
     recettes
    -0.59
     supérieurs
    -0.59
    POSITIVE LOGITS
     Waray
    0.58
    Portail
    0.56
    بوابة
    0.56
    <bos>
    0.56
     ongoing
    0.47
     visualisation
    0.45
    encodeWith
    0.45
    ⓧ
    0.45
    ised
    0.45
    atimes
    0.45
    Activations Density 0.018%

    No Known Activations