© 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. 1-RES-MATRYOSHKA-DC
    7. 334
    Prev
    Next
    INDEX
    Explanations

    references to the ordinal indicator "the" used as a formal marker or in expressions related to sequence or order

    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
     оригіналу
    -0.64
    NewUrlParser
    -0.60
     Sita
    -0.59
     aVar
    -0.58
    ExecuteReader
    -0.57
    vician
    -0.57
    pezi
    -0.57
    IOException
    -0.56
    ismet
    -0.56
    (;;)
    -0.55
    POSITIVE LOGITS
    th
    3.84
    TH
    2.70
    Th
    2.44
     th
    2.39
     Th
    2.19
     TH
    2.05
    ths
    1.98
    thd
    1.72
    thn
    1.66
    thm
    1.56
    Activations Density 0.866%

    No Known Activations