© 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. 1-RES-MATRYOSHKA-DC
    7. 1114
    Prev
    Next
    INDEX
    Explanations

    references to the document "the paper itself."

    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
     насеље
    -0.63
    Parcelize
    -0.59
    Autoritní
    -0.58
    invokeLater
    -0.55
    ceros
    -0.54
    bua
    -0.52
    deen
    -0.52
     numerus
    -0.52
    GraphicsUnit
    -0.51
    ARTER
    -0.51
    POSITIVE LOGITS
     itself
    5.06
    itself
    4.81
     Itself
    4.16
     themselves
    4.13
    themselves
    3.91
     himself
    3.48
     herself
    3.47
     Himself
    3.30
    himself
    3.23
    herself
    3.17
    Activations Density 0.115%

    No Known Activations