© 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. 24
    Prev
    Next
    INDEX
    Explanations

    descriptions of technical studies with mentions of characteristics, identification, and other related terms.

    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
    -
    -0.74
    b
    -0.73
    k
    -0.71
    z
    -0.71
    w
    -0.70
     up
    -0.68
    T
    -0.68
    p
    -0.66
     aryl
    -0.66
    Itoa
    -0.66
    POSITIVE LOGITS
     myſelf
    1.45
    BibitemShut
    1.39
     ―――――
    1.36
     itſelf
    1.36
    )");
    1.33
     ――――――――
    1.30
     ་་
    1.28
     themſelves
    1.23
     ſeveral
    1.18
     purpoſe
    1.15
    Activations Density 27.197%

    No Known Activations