© 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. 43072
    Prev
    Next
    INDEX
    Explanations

    driving

    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
    driving
    -2.19
     driving
    -2.03
    Driving
    -1.87
     Driving
    -1.83
     drove
    -1.05
    IsContent
    -1.03
    PerformLayout
    -0.98
    driver
    -0.98
    drives
    -0.96
     Driver
    -0.94
    POSITIVE LOGITS
    ron
    0.47
     incur
    0.46
     Legg
    0.45
    ts
    0.45
    ilya
    0.44
    orious
    0.43
    ler
    0.43
    nya
    0.43
     concern
    0.42
     intervention
    0.42
    Activations Density 0.232%

    No Known Activations