© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16200
    Prev
    Next
    INDEX
    Explanations

    a

    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
    Negative Logits
    脚注の使い方
    -0.62
     OFDb
    -0.56
    行政区划
    -0.55
    SuspendLayout
    -0.55
     znamen
    -0.53
    SourceChecksum
    -0.52
    Newswire
    -0.51
     lắm
    -0.51
     ejemplares
    -0.51
    edale
    -0.50
    POSITIVE LOGITS
     BoxFit
    0.72
     ton
    0.71
     bunch
    0.64
     (
    0.60
    whole
    0.59
    bunch
    0.57
     ddelweddau
    0.56
    mybatisplus
    0.55
     kotlinx
    0.55
     whole
    0.54
    Activations Density 0.089%

    No Known Activations