© 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. 3-RES-MATRYOSHKA-DC
    7. 1800
    Prev
    Next
    INDEX
    Explanations

    mentions of authors and manuscripts in a formal paper

    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
    MeasureSpec
    -0.60
     Jefus
    -0.60
     Monfieur
    -0.58
    leqq
    -0.56
     DialogInterface
    -0.54
    laints
    -0.54
     Efq
    -0.54
    certs
    -0.53
    mybatisplus
    -0.52
    agaimana
    -0.52
    POSITIVE LOGITS
     authors
    3.41
     Authors
    3.06
    Authors
    2.86
    authors
    2.81
     author
    2.78
     Author
    2.59
    author
    2.56
    Author
    2.42
     AUTHORS
    2.39
     autores
    2.22
    Activations Density 0.131%

    No Known Activations