© 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. 1-CLT-HP
    7. 10576
    Prev
    Next
    INDEX
    Explanations

    surface

    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
     surface
    -1.48
    surface
    -1.46
     Surface
    -1.38
    Surface
    -1.34
     SURFACE
    -1.30
    SURFACE
    -1.09
     superficie
    -0.96
     superfície
    -0.94
     surfaces
    -0.93
     Surfaces
    -0.92
    POSITIVE LOGITS
     tension
    0.65
    StoreMessageInfo
    0.65
     tensions
    0.60
     resistors
    0.57
     Tension
    0.57
     tannins
    0.56
    elerik
    0.56
    maxcdn
    0.55
     domestique
    0.55
    PathParam
    0.54
    Activations Density 0.059%

    No Known Activations