© 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. 20-CLT-HP
    7. 77566
    Prev
    Next
    INDEX
    Explanations

    Non-English text/code

    np_max-act-logits · 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
    IBinder
    -0.55
    GEBURTSDATUM
    -0.47
    PopupWindow
    -0.46
    JpaRepository
    -0.46
    TEMPO
    -0.45
    TabStop
    -0.44
     وتسجيلات
    -0.43
    eby
    -0.43
    cept
    -0.43
    зулта
    -0.43
    POSITIVE LOGITS
     समीक्षक
    0.58
    MigrationBuilder
    0.58
     Eme
    0.55
    Nir
    0.54
     otomatig
    0.54
     Gru
    0.53
     Bale
    0.53
    taxia
    0.52
    .='
    0.52
     }}"></
    0.52
    Activations Density 0.001%

    No Known Activations