© 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. 2-RES-MATRYOSHKA-DC
    7. 4072
    Prev
    Next
    INDEX
    Explanations

    structural elements related to edges and connections in diagrams or graphs

    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
    ed
    -0.87
    ED
    -0.75
     disponibilités
    -0.69
     Border
    -0.66
    border
    -0.64
     chart
    -0.64
    romyal
    -0.63
    )}-\
    -0.61
     Ed
    -0.60
    Portale
    -0.60
    POSITIVE LOGITS
     edge
    2.92
    edge
    2.69
    Edge
    2.67
     Edge
    2.64
     EDGE
    2.48
    EDGE
    2.30
     edges
    2.19
     Edges
    2.02
    edges
    1.93
    Edges
    1.73
    Activations Density 0.024%

    No Known Activations