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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93455
    Prev
    Next
    INDEX
    Explanations

    author

    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
    HasIndex
    -0.54
    ukone
    -0.50
     washer
    -0.48
     washers
    -0.45
    UIImageView
    -0.45
     QName
    -0.44
     Washer
    -0.44
    TileEntity
    -0.44
     streamer
    -0.43
    ClassPath
    -0.43
    POSITIVE LOGITS
    WriteTagHelper
    0.69
     of
    0.67
     Vikipedi
    0.64
    脚注の使い方
    0.59
    ValueStyle
    0.55
    hoeddwyd
    0.54
     فريبيس
    0.54
    erdings
    0.53
    esModule
    0.53
    ers
    0.50
    Activations Density 0.002%

    No Known Activations