© 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. 6006
    Prev
    Next
    INDEX
    Explanations

    references to code extensions or extension methods

    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
    SourceChecksum
    -0.90
     يتيمه
    -0.84
    OGND
    -0.81
     ويكيپيديا
    -0.79
    __':
    -0.78
     للاسماء
    -0.77
     للمعارف
    -0.77
     récomp
    -0.77
    SequentialGroup
    -0.75
     poichè
    -0.75
    POSITIVE LOGITS
     extension
    3.09
    extension
    2.95
     Extension
    2.91
    Extension
    2.86
     extensions
    2.66
     EXTENSION
    2.39
     Extensions
    2.33
    EXTENSION
    2.16
    extensions
    2.14
    Extensions
    1.97
    Activations Density 0.015%

    No Known Activations