© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45183
    Prev
    Next
    INDEX
    Explanations

    wd

    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
    wd
    -1.52
    WD
    -1.19
     WD
    -0.85
    ement
    -0.85
     wd
    -0.80
    edd
    -0.64
    complexContent
    -0.63
    antee
    -0.60
    WP
    -0.57
    ClientRect
    -0.55
    POSITIVE LOGITS
     poveznice
    0.61
    tvguidetime
    0.56
    IVEREF
    0.54
    WindowConstants
    0.53
     gills
    0.52
     byg
    0.49
    angun
    0.48
    randir
    0.48
     AssemblyCompany
    0.47
     Yap
    0.47
    Activations Density 0.145%

    No Known Activations