© 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. 6865
    Prev
    Next
    INDEX
    Explanations

    references to parentheses or brackets

    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
     I
    -0.62
     v
    -0.59
    fao
    -0.57
    <eos>
    -0.56
     di
    -0.55
    **/
    -0.55
     Ma
    -0.54
     V
    -0.53
     re
    -0.53
     of
    -0.52
    POSITIVE LOGITS
    (
    1.21
     Diſ
    1.17
     purpoſe
    1.17
     whoſe
    1.16
     Theſe
    1.14
     Monfieur
    1.14
     Inſ
    1.13
     ſever
    1.12
     Eſ
    1.12
     Efq
    1.12
    Activations Density 0.185%

    No Known Activations