© 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. 1-CLT-HP
    7. 16027
    Prev
    Next
    INDEX
    Explanations

    op

    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
    Negative Logits
     per
    -0.61
     pp
    -0.50
     simp
    -0.49
     Privacidade
    -0.49
    aliana
    -0.47
     avance
    -0.46
    CardBody
    -0.46
    CodeDom
    -0.45
    ambar
    -0.45
     womb
    -0.45
    POSITIVE LOGITS
     picioare
    0.65
     étoient
    0.63
     fidé
    0.60
    titleMargin
    0.58
    archiviato
    0.58
     oignons
    0.58
     uſed
    0.57
     aikaa
    0.56
    =$?
    0.56
     ModelExpression
    0.56
    Activations Density 0.067%

    No Known Activations