© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43098
    Prev
    Next
    INDEX
    Explanations

    triangular

    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
     étoient
    -0.91
     enfans
    -0.91
     avoient
    -0.86
     astore
    -0.73
     feroit
    -0.70
     charité
    -0.69
     auroit
    -0.68
     wikipagina
    -0.68
     debout
    -0.67
     Efq
    -0.66
    POSITIVE LOGITS
     to
    0.71
     незавершена
    0.57
    ly
    0.56
     set
    0.56
     stars
    0.55
     ra
    0.54
     turn
    0.54
     
    0.51
     power
    0.50
     level
    0.50
    Activations Density 0.096%

    No Known Activations