© 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. 2-RES-MATRYOSHKA-DC
    7. 5560
    Prev
    Next
    INDEX
    Explanations

    descriptions related to technical manufacturing processes or components

    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
     composition
    -0.70
     Composition
    -0.68
    composition
    -0.65
     compositions
    -0.63
    lielmo
    -0.62
     Compos
    -0.60
     COMPOSITION
    -0.60
    Composition
    -0.59
    zyst
    -0.58
    Puck
    -0.58
    POSITIVE LOGITS
     comprises
    1.70
     comprise
    1.62
     comprising
    1.57
     comprised
    1.04
    rrggbb
    0.95
     lenker
    0.85
    BagConstraints
    0.85
    featureID
    0.81
    tagHelperRunner
    0.80
     ControllerBase
    0.78
    Activations Density 0.007%

    No Known Activations