© 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. 95536
    Prev
    Next
    INDEX
    Explanations

    through

    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
     through
    -2.34
    through
    -1.96
     Through
    -1.71
    Through
    -1.70
     THROUGH
    -1.66
     melalui
    -1.59
     através
    -1.55
     attraverso
    -1.53
     través
    -1.49
     thru
    -1.38
    POSITIVE LOGITS
     Efq
    0.95
     the
    0.90
     purpoſe
    0.88
     ſmall
    0.84
     ſaid
    0.82
     houſe
    0.82
    ſelf
    0.81
     reaſon
    0.81
     ſind
    0.81
     uſe
    0.80
    Activations Density 0.059%

    No Known Activations