© 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. 6329
    Prev
    Next
    INDEX
    Explanations

    references to the formatting style "small caps."

    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
    IUrlHelper
    -0.77
    createCanvas
    -0.76
     ProtoMessage
    -0.69
     ConstraintSet
    -0.69
    parian
    -0.66
     flyknit
    -0.63
    Filmografie
    -0.62
    Demografia
    -0.61
    anyahu
    -0.61
    RUnlock
    -0.61
    POSITIVE LOGITS
    caps
    2.34
    Caps
    1.66
    CAPS
    1.54
     caps
    1.34
     CAPS
    1.34
     Caps
    1.28
    capsulation
    1.15
     encaps
    0.95
     capsule
    0.92
    capsule
    0.90
    Activations Density 0.020%

    No Known Activations