© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5954
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or judicial opinions, specifically references to "pur" indicating "pursuant" or related legal citations and discussions

    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
    %">
    -0.68
    WriteTagHelper
    -0.67
    Vege
    -0.65
    )':
    -0.64
    !*\
    -0.62
     InputDecoration
    -0.59
     Eks
    -0.59
     оригіналу
    -0.59
    Geplaatst
    -0.56
    Testimonial
    -0.56
    POSITIVE LOGITS
    Pur
    2.88
    pur
    2.61
     Pur
    2.38
     PUR
    2.36
     pursuit
    2.20
     pursue
    2.19
     Pursu
    2.19
     pursuing
    2.14
     Pursuit
    2.09
     pursued
    2.08
    Activations Density 0.045%

    No Known Activations