© 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. 6119
    Prev
    Next
    INDEX
    Explanations

    sequences of tokens involving numeric terms, symbols, and the keyword "Collect" with varying relevance

    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
     Collection
    -1.05
    collection
    -1.00
     collection
    -0.99
     COLLECTION
    -0.95
    Collection
    -0.93
     collections
    -0.82
    COLLECTION
    -0.81
     Collections
    -0.76
     colección
    -0.72
    collections
    -0.68
    POSITIVE LOGITS
    Collect
    1.87
     Collect
    1.63
    collect
    1.61
     collect
    1.34
    COLLECT
    1.24
     collects
    1.11
     COLLECT
    1.07
     Collecting
    1.06
    Collecting
    1.06
     collecting
    1.04
    Activations Density 0.021%

    No Known Activations