© 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. 5-CLT-HP
    4. 891
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    IntoConstraints
    -0.67
    migrationBuilder
    -0.66
    stunden
    -0.65
     NSCoder
    -0.61
    ViewInit
    -0.60
     autorytatywna
    -0.59
     defStyleAttr
    -0.59
     Values
    -0.57
     CreateTagHelper
    -0.57
    GOTREF
    -0.56
    POSITIVE LOGITS
    ptonshire
    0.47
    ttemberg
    0.47
    TintMode
    0.45
    transforms
    0.41
    pholes
    0.39
     sou
    0.39
     elegans
    0.39
     himo
    0.39
     igre
    0.38
    RegisterType
    0.38
    Activations Density 0.002%

    No Known Activations