© 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. 306
    Prev
    Next
    INDEX
    Explanations

    rules defining allowable cycles and dependencies in directed graph structures

    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
    -0.54
    zbęd
    -0.52
    WithFormat
    -0.50
     poffible
    -0.48
     houſe
    -0.48
    belea
    -0.46
    horizontalLayout
    -0.46
     fevere
    -0.45
     poffe
    -0.45
    herjee
    -0.44
    POSITIVE LOGITS
     G
    3.03
    G
    2.88
     g
    2.83
    g
    2.56
    Gs
    1.82
    Ｇ
    1.79
     Gs
    1.59
    ｇ
    1.53
     Г
    1.48
     ग
    1.48
    Activations Density 1.515%

    No Known Activations