© 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. 7168
    Prev
    Next
    INDEX
    Explanations

    key mathematical expressions and notations related to energy, surface energies, and statistical models

    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
    AsUp
    -0.63
    runApp
    -0.60
    spender
    -0.59
     Barrow
    -0.56
     Weston
    -0.54
    bar
    -0.50
    tillon
    -0.50
     ?
    -0.49
    Lax
    -0.49
    ご了承ください
    -0.49
    POSITIVE LOGITS
    textbf
    3.58
    textit
    1.80
    emph
    1.02
    textsc
    0.86
    DispatchToProps
    0.79
     PTT
    0.73
    Datuak
    0.72
     intptr
    0.69
    maketitle
    0.68
    BibitemShut
    0.68
    Activations Density 0.001%

    No Known Activations