© 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. 405
    Prev
    Next
    INDEX
    Explanations

    definitions or mentions of specific structured codes or notation, often associated with mathematical or technical language

    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
    k
    -0.94
    n
    -0.89
    t
    -0.82
    l
    -0.82
    ng
    -0.81
    m
    -0.79
    r
    -0.79
    ly
    -0.76
    p
    -0.75
    ling
    -0.75
    POSITIVE LOGITS
     LDA
    1.20
     CDA
    1.15
     MSA
    1.13
     IMA
    1.13
     CMA
    1.12
     TPA
    1.12
     NLA
    1.11
     MDA
    1.10
     MCA
    1.09
     TDA
    1.09
    Activations Density 3.578%

    No Known Activations