© 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. 78230
    Prev
    Next
    INDEX
    Explanations

    technical/research contexts

    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
     חיצוניים
    -0.54
     دیکھیے
    -0.44
    ोंने
    -0.44
    ("$.
    -0.43
    XmlAccessType
    -0.42
    medim
    -0.42
    पया
    -0.42
    roek
    -0.40
    Affection
    -0.40
     héroes
    -0.39
    POSITIVE LOGITS
    parsedMessage
    0.70
     sund
    0.65
     &___
    0.63
     kasarigan
    0.62
     g
    0.59
    awaiter
    0.57
    WebVitals
    0.53
     sortes
    0.52
    IndentedString
    0.52
    WebElementEntity
    0.52
    Activations Density 0.000%

    No Known Activations