© 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. 652
    Prev
    Next
    INDEX
    Explanations

    references to the concept of an edge or connection in a graph

    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
     AppCompat
    -0.68
    romyal
    -0.67
    ToScroll
    -0.65
    xmlWriter
    -0.63
    >*/
    -0.61
     chiare
    -0.60
    rolo
    -0.60
    atelyn
    -0.60
    publique
    -0.57
    MarshalTo
    -0.56
    POSITIVE LOGITS
     edge
    4.72
    edge
    4.28
     Edge
    4.25
    Edge
    4.09
     EDGE
    3.77
     edges
    3.75
    EDGE
    3.50
     Edges
    3.44
    edges
    3.14
    Edges
    3.03
    Activations Density 0.687%

    No Known Activations