© 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. 15436
    Prev
    Next
    INDEX
    Explanations

    image

    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
     Audiodateien
    -0.52
     '\\;'
    -0.50
    AddTagHelper
    -0.50
    Pautan
    -0.48
     StatefulWidget
    -0.47
    usermodel
    -0.47
    存于互联网档案馆
    -0.46
     psycopg
    -0.45
    lotl
    -0.45
    /***/
    -0.44
    POSITIVE LOGITS
    chauung
    0.61
     nahilalakip
    0.60
    räger
    0.59
     bête
    0.59
     Надо
    0.58
    trine
    0.54
    Географиясе
    0.54
    ArrayOf
    0.53
    liable
    0.53
    पया
    0.53
    Activations Density 0.005%

    No Known Activations