© 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. 8703
    Prev
    Next
    INDEX
    Explanations

    ize/ise

    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
    yayım
    -0.49
    ség
    -0.49
    qualification
    -0.48
    izations
    -0.47
     engraçadas
    -0.46
    mentary
    -0.46
    queous
    -0.46
    ments
    -0.45
    desarrollo
    -0.45
    PROCESSING
    -0.45
    POSITIVE LOGITS
    AndEndTag
    1.05
    XmlAccessType
    0.89
     of
    0.85
    __':
    0.79
    __':
    0.77
    parsedMessage
    0.75
     mergeFrom
    0.73
    urlpatterns
    0.68
    setVerticalGroup
    0.68
    BeginContext
    0.63
    Activations Density 0.078%

    No Known Activations