© 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. 694
    Prev
    Next
    INDEX
    Explanations

    the word "search", sometimes with the words "for", "algorithm", or "strategy"

    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
    Tikang
    -0.81
     deltaTime
    -0.73
    WriteTagHelper
    -0.69
    ✨:
    -0.68
    LayoutPanel
    -0.68
    contentLoaded
    -0.66
    iarkan
    -0.64
     gustó
    -0.64
    StructEnd
    -0.64
     Enix
    -0.63
    POSITIVE LOGITS
     search
    3.36
     Search
    3.02
     SEARCH
    2.91
    search
    2.88
    Search
    2.88
     searches
    2.77
    SEARCH
    2.75
     searching
    2.63
     searched
    2.61
     Searches
    2.55
    Activations Density 0.638%

    No Known Activations