© 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. 6-RES-MATRYOSHKA-DC
    7. 417
    Prev
    Next
    INDEX
    Explanations

    words associated with performing an operation or task, especially in the context of a system or machine.

    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
     concerns
    -0.66
    받
    -0.65
     Concerns
    -0.63
     stig
    -0.60
    ప్ప
    -0.59
     viewType
    -0.59
    marle
    -0.58
     prejud
    -0.57
    Pageable
    -0.56
    Stig
    -0.56
    POSITIVE LOGITS
     operate
    1.38
     operated
    1.28
     Operate
    1.27
     functions
    1.18
     operates
    1.18
     execute
    1.16
     operating
    1.15
    operated
    1.14
     function
    1.13
     operation
    1.13
    Activations Density 2.535%

    No Known Activations