© 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. 185
    Prev
    Next
    INDEX
    Explanations

    patterns involving algebraic structures, matrices, and linear independence concepts

    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
    b
    -1.25
    c
    -1.00
    f
    -0.90
    h
    -0.90
    r
    -0.81
    m
    -0.79
    g
    -0.79
    p
    -0.77
    q
    -0.75
    d
    -0.73
    POSITIVE LOGITS
     E
    1.44
     D
    1.43
     M
    1.27
     P
    1.26
     A
    1.20
     F
    1.20
     O
    1.20
     W
    1.15
     R
    1.10
     G
    1.10
    Activations Density 4.197%

    No Known Activations