© 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. 11828
    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
    -1.34
    surface
    -1.30
     Surface
    -1.28
    Surface
    -1.27
     SURFACE
    -1.20
    SURFACE
    -1.16
     Surfaces
    -1.09
     surfaces
    -1.05
     superficie
    -1.04
     superfície
    -1.03
    POSITIVE LOGITS
    RenderAtEndOf
    0.90
    enderror
    0.73
    StoryboardSegue
    0.72
    ScopeManager
    0.70
     CreateTagHelper
    0.68
    hoeddwyd
    0.67
    AxisAlignment
    0.65
    DockStyle
    0.63
     numerus
    0.63
    brainly
    0.60
    Activations Density 0.014%

    No Known Activations