© 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. 2-RES-MATRYOSHKA-DC
    7. 3454
    Prev
    Next
    INDEX
    Explanations

    references to dependency information within build configuration or code files

    oai_token-act-pair · gpt-4.1-nano
    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
    NUMX
    -0.78
     depending
    -0.77
    PYX
    -0.76
    depending
    -0.76
     Depending
    -0.71
    Depending
    -0.70
     dependiendo
    -0.69
    tagext
    -0.66
     resourceCulture
    -0.65
    RegistryLite
    -0.64
    POSITIVE LOGITS
     dependencies
    2.36
    dependencies
    2.30
     Dependencies
    1.98
     dependency
    1.95
     Dependency
    1.83
    Dependencies
    1.80
    Dependency
    1.75
    dependency
    1.59
     deps
    1.11
    Deps
    0.97
    Activations Density 0.009%

    No Known Activations