© 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. 7088
    Prev
    Next
    INDEX
    Explanations

    references to instances where something is actively being shown or illustrated

    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
    parsedMessage
    -0.94
    ImageContext
    -0.89
    expandindo
    -0.85
    клопе
    -0.84
    HandlerContext
    -0.79
     مشين
    -0.77
     BoxFit
    -0.76
     GenerationType
    -0.76
    databind
    -0.72
     guineas
    -0.71
    POSITIVE LOGITS
     showcase
    0.82
     showcases
    0.80
     showcased
    0.80
     displays
    0.77
     showcasing
    0.71
     displayed
    0.66
     displaying
    0.60
     demonstrates
    0.59
     Showcase
    0.58
    displayed
    0.58
    Activations Density 0.011%

    No Known Activations