© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78154
    Prev
    Next
    INDEX
    Explanations

    over

    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
    Negative Logits
    posedge
    -0.55
    galus
    -0.55
    fromCharCode
    -0.50
    weile
    -0.50
     للمعارف
    -0.49
    مراجع
    -0.49
    elts
    -0.47
    __*/
    -0.47
    Παραπομπές
    -0.46
    __":
    -0.45
    POSITIVE LOGITS
    UnusedPrivate
    0.60
    Hozzáférés
    0.60
     Roskov
    0.59
    MessageTagHelper
    0.57
     متعلقه
    0.55
    BeginContext
    0.55
     kasarigan
    0.54
    peño
    0.54
     referenties
    0.52
     ErrIntOverflow
    0.52
    Activations Density 0.000%

    No Known Activations