© 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. 2669
    Prev
    Next
    INDEX
    Explanations

    sentences or statements that are primarily composed of periods (full stops)

    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
    Negative Logits
    צלחה
    -0.61
    Personendaten
    -0.60
     Bucc
    -0.57
     Szw
    -0.54
     fortunately
    -0.52
    رشف
    -0.52
    clubs
    -0.52
     zirc
    -0.52
    ostante
    -0.51
     viſ
    -0.51
    POSITIVE LOGITS
    *
    0.73
    WebServlet
    0.67
    afficheront
    0.63
    WebElementEntity
    0.63
     *
    0.60
     հղումներ
    0.54
    chromedriver
    0.54
    enumerate
    0.53
     invokingState
    0.53
    arika
    0.52
    Activations Density 0.147%

    No Known Activations