© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5673
    Prev
    Next
    INDEX
    Explanations

    references to the envelope, directions, and staging in various contexts

    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
    awaiter
    -0.56
     dolayı
    -0.50
    گزاری
    -0.48
    AndEndTag
    -0.47
    #
    -0.47
    ವು
    -0.46
     participó
    -0.45
     død
    -0.45
     sırasında
    -0.44
    ﷺ
    -0.44
    POSITIVE LOGITS
    RenderAtEndOf
    0.82
     Richelieu
    0.76
     curtain
    0.70
     paradise
    0.69
     curtains
    0.69
     crescendo
    0.69
     lifeline
    0.69
     roost
    0.68
     salvation
    0.67
    daging
    0.67
    Activations Density 1.334%

    No Known Activations