© 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. 4701
    Prev
    Next
    INDEX
    Explanations

    references to internal register identifiers

    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
    olella
    -0.63
     Barney
    -0.62
     canst
    -0.60
    SequentialGroup
    -0.59
     Horton
    -0.59
    messageInfo
    -0.58
     Benny
    -0.57
     InputDecoration
    -0.57
    exitRule
    -0.57
    Diweddarwch
    -0.57
    POSITIVE LOGITS
    IR
    3.20
    ir
    3.00
     IR
    2.92
     Ir
    2.36
     ir
    2.31
    Ir
    2.27
    irs
    1.70
     infrared
    1.63
     Infrared
    1.56
    Infrared
    1.46
    Activations Density 0.133%

    No Known Activations