© 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. 3132
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific technical resource identifiers or code-related tags

    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
     متعلقه
    -0.77
     Efq
    -0.73
     bezeichneter
    -0.72
     Maude
    -0.70
    =$?
    -0.66
     onCancelled
    -0.66
     Heinemann
    -0.65
    DataSetChanged
    -0.64
     Lewiston
    -0.64
    estad
    -0.63
    POSITIVE LOGITS
    dl
    3.23
    DL
    3.03
     DL
    2.58
     dl
    2.41
    Dl
    1.77
    dL
    1.57
    dlc
    0.94
    dla
    0.92
    sdl
    0.90
    BDL
    0.90
    Activations Density 0.017%

    No Known Activations