© 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. 6439
    Prev
    Next
    INDEX
    Explanations

    references to the concept of a "pat" or "patent"

    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
    MigrationBuilder
    -0.74
    Geplaatst
    -0.70
     AssemblyCulture
    -0.65
    клопе
    -0.63
    קישורים
    -0.62
     digress
    -0.61
    IndentedString
    -0.60
    expandindo
    -0.60
    تقاوى
    -0.59
    BeginContext
    -0.56
    POSITIVE LOGITS
     pat
    2.20
    pat
    2.14
     PAT
    2.06
    PAT
    2.03
    Pat
    1.70
     pats
    1.49
    pats
    1.45
     Pat
    1.44
     patro
    1.32
    patron
    1.27
    Activations Density 0.028%

    No Known Activations