© 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. 46057
    Prev
    Next
    INDEX
    Explanations

    Lau

    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
     live
    -0.80
    帖最后由
    -0.72
    live
    -0.66
    Live
    -0.66
    ValueStyle
    -0.64
    IntoConstraints
    -0.61
    posedge
    -0.59
    blico
    -0.57
     AssemblyCulture
    -0.56
     Live
    -0.55
    POSITIVE LOGITS
     AssemblyCompany
    0.75
    Espèce
    0.64
     FontWeight
    0.62
     huom
    0.55
     meille
    0.54
    Detector
    0.52
     Савезне
    0.51
    complexContent
    0.51
     testemun
    0.51
     Breaks
    0.49
    Activations Density 0.014%

    No Known Activations