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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45906
    Prev
    Next
    INDEX
    Explanations

    drive

    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
     drive
    -1.26
    drive
    -1.20
     Drive
    -1.03
    Drive
    -0.99
     DRIVE
    -0.97
     drives
    -0.88
     driving
    -0.88
     Drives
    -0.84
    driving
    -0.83
    drives
    -0.81
    POSITIVE LOGITS
     letter
    0.61
    RUnlock
    0.58
    letter
    0.56
     lit
    0.54
    LETTER
    0.53
    Letter
    0.52
    ichthys
    0.51
     Letter
    0.51
     setter
    0.51
     letters
    0.48
    Activations Density 0.008%

    No Known Activations