© 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. 2144
    Prev
    Next
    INDEX
    Explanations

    words related to different kinds of procedures or processes

    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
     realising
    -0.85
     AssemblyCompany
    -0.83
     realizing
    -0.79
     EconPapers
    -0.77
    queryInterface
    -0.77
     mergeFrom
    -0.76
    ScopeManager
    -0.73
    OrNil
    -0.71
    InjectAttribute
    -0.70
    being
    -0.69
    POSITIVE LOGITS
    Baking
    0.81
    Farming
    0.75
     Baking
    0.74
     baking
    0.74
    xing
    0.71
     Farming
    0.70
     Voting
    0.69
    Coding
    0.68
    coding
    0.68
    farming
    0.67
    Activations Density 0.813%

    No Known Activations