© 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. 0-CLT-HP
    7. 95494
    Prev
    Next
    INDEX
    Explanations

    Abstract concepts and change

    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
    Not in Any Lists

    No Comments

    Negative Logits
    WithMany
    -0.67
    XmlAccessType
    -0.65
     closure
    -0.63
    XmlEnum
    -0.60
    jsoup
    -0.60
     BorderLayout
    -0.59
     ivelany
    -0.57
     exploit
    -0.56
    SuppressLint
    -0.54
    principalColumn
    -0.54
    POSITIVE LOGITS
     oprot
    0.54
    ᅠ
    0.53
     referenties
    0.50
    liceerd
    0.48
     sportifs
    0.47
    SharedCtor
    0.47
     aand
    0.46
    Anhalt
    0.46
     فريبيس
    0.46
    novu
    0.44
    Activations Density 0.023%

    No Known Activations