© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14530
    Prev
    Next
    INDEX
    Explanations

    plating/coating

    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
    plated
    -1.27
    plating
    -1.10
     plating
    -1.07
     plated
    -1.02
     Plated
    -0.97
    coating
    -0.79
     Coating
    -0.77
     coating
    -0.77
    StructEnd
    -0.74
     Coated
    -0.73
    POSITIVE LOGITS
     ochi
    0.50
    cookieParser
    0.45
     amet
    0.44
    ing
    0.43
    nh
    0.41
    zina
    0.41
     let
    0.40
    enko
    0.39
    buttonShape
    0.39
    BorderFactory
    0.39
    Activations Density 0.025%

    No Known Activations