© 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. 5774
    Prev
    Next
    INDEX
    Explanations

    references to the word "By" at the beginning of sentences or phrases

    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
     datang
    -0.47
     dialami
    -0.46
    なった
    -0.45
     Earlier
    -0.44
     Coming
    -0.43
    hány
    -0.43
    現實
    -0.43
    experienced
    -0.43
    ージャ
    -0.43
    IMPORTED
    -0.42
    POSITIVE LOGITS
    By
    2.45
     By
    2.39
    BY
    1.59
     BY
    1.50
     getBy
    1.17
     Byr
    1.15
    by
    1.07
     Bye
    1.05
    byr
    1.04
    bys
    1.03
    Activations Density 0.064%

    No Known Activations