© 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. 2-RES-MATRYOSHKA-DC
    7. 7399
    Prev
    Next
    INDEX
    Explanations

    references to traffic-related issues

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AppCompatTheme
    -0.57
    imah
    -0.54
    प्त
    -0.52
    LabelTagHelper
    -0.51
     imprese
    -0.51
    Boas
    -0.50
    println
    -0.50
    CONNECTED
    -0.50
    地上
    -0.49
    cruz
    -0.49
    POSITIVE LOGITS
     traffic
    3.69
     Traffic
    3.47
    traffic
    3.44
    Traffic
    3.41
     TRAFFIC
    3.03
     trafic
    2.19
     tráfico
    2.17
     trafik
    2.03
     traffico
    2.02
     traff
    1.90
    Activations Density 0.012%

    No Known Activations