© 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. 0-RES-MATRYOSHKA-DC
    7. 10405
    Prev
    Next
    INDEX
    Explanations

    specific types of embedded URL patterns, especially those indicating links or references within HTML or markdown code

    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
    ;/
    -0.65
    :/
    -0.61
     '/
    -0.57
     thermique
    -0.52
     aguda
    -0.51
     dichiarato
    -0.49
     "/
    -0.49
     sociales
    -0.49
    št
    -0.48
     sociais
    -0.47
    POSITIVE LOGITS
    ="/
    2.38
    ='/
    1.39
    ="./
    1.19
    ="/">
    1.05
    ="/"
    0.92
    ={`/
    0.85
     calendriers
    0.73
     BoxDecoration
    0.69
    ArgumentParser
    0.68
     NLI
    0.66
    Activations Density 0.005%

    No Known Activations