© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76226
    Prev
    Next
    INDEX
    Explanations

    Off and pro

    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
    Offering
    -0.90
     Offering
    -0.88
    offering
    -0.84
    Offered
    -0.81
    offered
    -0.80
    CloseOperation
    -0.79
     Offered
    -0.77
    awaiter
    -0.76
     Available
    -0.75
    available
    -0.75
    POSITIVE LOGITS
     off
    0.70
     o
    0.70
     pro
    0.63
     Off
    0.54
     Pro
    0.50
     о
    0.49
    pro
    0.47
    Off
    0.47
    Pro
    0.46
    off
    0.45
    Activations Density 0.007%

    No Known Activations