© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43798
    Prev
    Next
    INDEX
    Explanations

    Flushing or covering surfaces

    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
     covered
    -1.88
     Covered
    -1.74
    covered
    -1.66
    Covered
    -1.62
     cubierto
    -1.09
     flush
    -1.05
     enclosed
    -1.01
     couverts
    -1.01
     cubiertos
    -1.00
     couvert
    -0.91
    POSITIVE LOGITS
    AddTagHelper
    0.77
    s
    0.66
     Normdatei
    0.58
    RunWith
    0.54
    rifuge
    0.54
     defaultstate
    0.53
     by
    0.52
     Wikimedijinoj
    0.52
     parseFrom
    0.52
    ColumnHeaders
    0.51
    Activations Density 1.529%

    No Known Activations