© 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. 5-CLT-HP
    7. 6090
    Prev
    Next
    INDEX
    Explanations

    LCD

    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
    twimg
    -0.83
    urlpatterns
    -0.70
     pandémie
    -0.65
    ValueStyle
    -0.65
    DockStyle
    -0.65
     vectorstock
    -0.62
    مقاله
    -0.62
    AnchorStyles
    -0.60
     autorytatywna
    -0.60
     öffnungszeiten
    -0.60
    POSITIVE LOGITS
     
    0.52
    المناصب
    0.46
     Sh
    0.42
     Fa
    0.41
     lô
    0.40
    eX
    0.39
    4
    0.39
    ています
    0.39
    aragus
    0.39
     series
    0.38
    Activations Density 0.001%

    No Known Activations