© 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. 71622
    Prev
    Next
    INDEX
    Explanations

    in

    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
    Not in Any Lists

    No Comments

    Negative Logits
     onCancelled
    -0.56
    WebControls
    -0.51
     useStyles
    -0.48
     ""}
    -0.48
     utafitiHapana
    -0.47
     Draht
    -0.47
     poveznice
    -0.46
     linked
    -0.46
    UserScript
    -0.45
     متعلقه
    -0.45
    POSITIVE LOGITS
     virtue
    0.59
    BagLayout
    0.55
     appré
    0.54
    WebElementEntity
    0.54
     Issue
    0.53
    adpleegd
    0.50
     issue
    0.49
     réservation
    0.48
    PhysRevD
    0.48
    ništ
    0.47
    Activations Density 0.009%

    No Known Activations