© 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. 0-CLT-HP
    7. 1944
    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
    -2.16
    surface
    -1.91
     Surface
    -1.78
    Surface
    -1.70
     SURFACE
    -1.66
    SURFACE
    -1.34
     superficie
    -1.31
     superfície
    -1.30
    表面
    -1.23
     surfaces
    -1.22
    POSITIVE LOGITS
    parsedMessage
    0.90
    TypedDataSet
    0.80
    Хьажоргаш
    0.80
    StoryboardSegue
    0.76
    webElementXpaths
    0.74
    ertale
    0.72
    CDCl
    0.72
    TestingModule
    0.71
    extAlignment
    0.69
    ChildScrollView
    0.68
    Activations Density 0.134%

    No Known Activations