© 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. 71597
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    AutoField
    -0.56
    quem
    -0.47
     co
    -0.47
    mante
    -0.47
    mend
    -0.44
     Land
    -0.44
    lados
    -0.44
    ment
    -0.44
    porte
    -0.43
     Blan
    -0.43
    POSITIVE LOGITS
    UserScript
    0.77
     CreateTagHelper
    0.73
    存于互联网档案馆
    0.71
     للمعارف
    0.66
     wireType
    0.66
     viewDidLoad
    0.65
    parsedMessage
    0.63
    IUrlHelper
    0.63
     referenties
    0.62
     ویکی‌پدیای
    0.61
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.