© 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. 633
    Prev
    Next
    INDEX
    Explanations

    veneer

    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
     فريبيس
    -0.75
     veneers
    -0.67
     kV
    -0.65
    Sucesor
    -0.63
    Personensuche
    -0.56
     Audiodateien
    -0.56
     jaro
    -0.56
     المعيارى
    -0.55
     FBref
    -0.55
    цездатний
    -0.55
    POSITIVE LOGITS
    RTLD
    0.57
    AsUp
    0.51
    sizeCache
    0.50
     Lander
    0.47
     Salad
    0.47
    thday
    0.46
    Stuttgart
    0.45
     Resid
    0.45
     Salt
    0.44
     Soil
    0.43
    Activations Density 0.037%

    No Known Activations