© 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. 6-RES-MATRYOSHKA-DC
    7. 1107
    Prev
    Next
    INDEX
    Explanations

    a mix of abbreviations, names, and references that may come from different languages.

    oai_token-act-pair · gemini-2.0-flash
    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
     Sitten
    -0.73
    Сайт
    -0.70
     MCI
    -0.68
     CITES
    -0.67
     spokoj
    -0.66
    ContextHolder
    -0.66
     Allu
    -0.66
     Charlemagne
    -0.65
     kites
    -0.65
     DSS
    -0.64
    POSITIVE LOGITS
     Gub
    1.18
    jeb
    1.13
     Wib
    1.12
     Eub
    1.09
    UB
    1.09
    lob
    1.09
    Teb
    1.09
     Mb
    1.07
    tub
    1.07
     Dab
    1.07
    Activations Density 1.510%

    No Known Activations