© 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. 4303
    Prev
    Next
    INDEX
    Explanations

    references to small, specific portions or segments of data or objects

    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
    MLLoader
    -0.75
    دارة
    -0.63
    ACTIVITY
    -0.60
     Völker
    -0.59
    Попис
    -0.59
     Mayfield
    -0.57
     nahilalakip
    -0.57
     Pellegrini
    -0.57
     tyre
    -0.56
    пати
    -0.55
    POSITIVE LOGITS
     piece
    3.75
     pieces
    3.66
    piece
    3.44
     Piece
    3.41
    pieces
    3.41
     Pieces
    3.34
     PIECE
    3.28
    Piece
    3.22
    Pieces
    3.11
    PIECE
    2.69
    Activations Density 0.034%

    No Known Activations