© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1208
    Prev
    Next
    INDEX
    Explanations

    the word "expression" followed by "of"

    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
    jooq
    -0.67
     MacLeod
    -0.67
     cellpadding
    -0.66
     Lucre
    -0.64
     Macle
    -0.64
     Bakar
    -0.64
    DataAnnotations
    -0.62
    addGap
    -0.61
    BackStack
    -0.61
     Olms
    -0.61
    POSITIVE LOGITS
     expression
    2.59
     Expression
    2.47
    expression
    2.45
     expressions
    2.34
     EXPRESS
    2.27
    Expression
    2.25
     express
    2.19
     Express
    2.16
     Expressions
    2.14
    expressions
    2.14
    Activations Density 0.373%

    No Known Activations