© 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. 1010
    Prev
    Next
    INDEX
    Explanations

    the word "operation" in various contexts, sometimes including the preposition "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
     Carrillo
    -0.67
     Chriftian
    -0.65
     Vara
    -0.65
     Gson
    -0.63
     Gatsby
    -0.63
    CppCodeGen
    -0.63
     Lübeck
    -0.62
     fuch
    -0.62
    andidaten
    -0.62
    abbix
    -0.62
    POSITIVE LOGITS
     operation
    2.97
     operations
    2.73
     Operation
    2.73
     operate
    2.59
    operation
    2.59
     OPERATION
    2.58
     oper
    2.55
     operated
    2.52
    Operation
    2.50
     Operations
    2.50
    Activations Density 0.450%

    No Known Activations