© 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. 6160
    Prev
    Next
    INDEX
    Explanations

    references to scientific diagrams or figures

    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
     Table
    -1.55
    Table
    -1.48
     table
    -0.88
     Tables
    -0.87
     TABLE
    -0.77
    Tables
    -0.70
    Таблица
    -0.66
     tabled
    -0.63
     tables
    -0.60
    表
    -0.59
    POSITIVE LOGITS
     Fig
    1.24
    Fig
    1.23
    httphttps
    0.91
     Figs
    0.86
    EDEFAULT
    0.83
     fig
    0.80
     للمعارف
    0.78
    +:+
    0.77
    Figs
    0.74
    LLocation
    0.74
    Activations Density 0.055%

    No Known Activations