© 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. 95482
    Prev
    Next
    INDEX
    Explanations

    scientific articles

    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
     well
    -0.89
    well
    -0.76
    wel
    -0.75
     swelling
    -0.71
     WELL
    -0.69
    itism
    -0.69
     Well
    -0.68
    WELL
    -0.67
    WEL
    -0.66
     reasoning
    -0.65
    POSITIVE LOGITS
     surla
    0.59
     '\\;'
    0.57
     désolés
    0.55
    urlpatterns
    0.52
    withIdentifier
    0.51
    googleapis
    0.50
    IDENTIFIED
    0.50
    nocache
    0.50
    ー
    0.50
     onSubmit
    0.50
    Activations Density 0.260%

    No Known Activations