© 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. 3-RES-MATRYOSHKA-DC
    7. 1668
    Prev
    Next
    INDEX
    Explanations

    the phrase "subject to"

    oai_token-act-pair · gemini-2.0-flash
    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
    ForRow
    -0.71
    ReusableCell
    -0.69
     GenerationType
    -0.65
     Weisheit
    -0.65
    enterOuterAlt
    -0.64
    óns
    -0.62
     kasarigan
    -0.61
    writerow
    -0.61
     TextAlign
    -0.60
    TypedDataSet
    -0.59
    POSITIVE LOGITS
     subject
    4.03
    subject
    3.64
     Subject
    3.61
    Subject
    3.44
     SUBJECT
    3.23
     subjects
    3.22
    SUBJECT
    3.00
     Subjects
    2.95
    subjects
    2.75
    Subjects
    2.56
    Activations Density 0.080%

    No Known Activations