© 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. 71646
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
     see
    -1.11
    see
    -0.97
    sees
    -0.96
     SEE
    -0.93
     resourceCulture
    -0.91
     sees
    -0.90
    SEE
    -0.89
     See
    -0.87
     initComponents
    -0.84
     Lihat
    -0.82
    POSITIVE LOGITS
     fiind
    0.32
     antena
    0.32
     siano
    0.30
     là
    0.29
    kund
    0.28
     posteriore
    0.27
    PCell
    0.27
    кто
    0.27
     si
    0.26
     teken
    0.26
    Activations Density 0.000%

    No Known Activations