© 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. 1-RES-MATRYOSHKA-DC
    7. 237
    Prev
    Next
    INDEX
    Explanations

    questions or prompts asking for specific information

    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
     which
    -3.09
    which
    -2.69
     WHICH
    -2.44
     Which
    -2.23
    Which
    -2.16
    hich
    -1.77
     które
    -1.66
    ซึ่ง
    -1.63
     которое
    -1.57
     ซึ่ง
    -1.57
    POSITIVE LOGITS
     what
    2.05
    what
    1.95
    What
    1.88
     What
    1.88
     WHAT
    1.62
    WHAT
    1.54
     hva
    1.09
     whats
    1.08
     hvad
    1.07
    whats
    1.06
    Activations Density 0.159%

    No Known Activations