© 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. 0-RES-MATRYOSHKA-DC
    7. 12157
    Prev
    Next
    INDEX
    Explanations

    patterns involving the number of items selected, often indicating the neuron detects the act of repeatedly choosing a specific number of elements from a collection

    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
     pick
    -1.05
    pick
    -1.04
    Pick
    -0.96
     Pick
    -0.89
     PICK
    -0.79
    PICK
    -0.75
     Efq
    -0.75
     photolibrary
    -0.75
    drawal
    -0.73
     pleaſure
    -0.72
    POSITIVE LOGITS
     picked
    1.34
     selected
    1.08
    selected
    0.95
     Selected
    0.91
    picked
    0.88
     chosen
    0.85
    Selected
    0.85
     SELECTED
    0.79
    SELECTED
    0.71
     bought
    0.68
    Activations Density 0.004%

    No Known Activations