© 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-RES-MATRYOSHKA-DC
    7. 1396
    Prev
    Next
    INDEX
    Explanations

    references to legal arguments or reasoning

    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
     mystery
    -0.58
    Mystery
    -0.57
     Shades
    -0.57
     Dominus
    -0.56
     Mystery
    -0.55
    CodeAttribute
    -0.53
     بيها
    -0.53
     azzurro
    -0.53
     tapis
    -0.52
    花板
    -0.52
    POSITIVE LOGITS
     argument
    4.31
     arguments
    3.94
    argument
    3.81
     Argument
    3.77
     Arguments
    3.47
    Argument
    3.45
    arguments
    3.39
     ARGUMENT
    3.22
     argue
    3.03
    Arguments
    2.95
    Activations Density 0.252%

    No Known Activations