© 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. 6010
    Prev
    Next
    INDEX
    Explanations

    how

    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
     MongoClient
    -0.53
     finishing
    -0.52
     Finished
    -0.51
    +/**
    -0.50
    Autoritní
    -0.50
    
    -0.50
     Finishing
    -0.50
    oldt
    -0.48
    uegos
    -0.48
     finished
    -0.48
    POSITIVE LOGITS
    InjectAttribute
    0.93
    setVerticalGroup
    0.65
     appunt
    0.60
     refirió
    0.59
    httphttps
    0.54
    RenderAtEndOf
    0.52
     myſelf
    0.52
    ungsbedingungen
    0.48
     appuntamento
    0.48
     Suède
    0.47
    Activations Density 0.021%

    No Known Activations