© 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. 3492
    Prev
    Next
    INDEX
    Explanations

    the presence of complex graph structures, specifically cycles, adjacency relationships, and parent-child relationships within a directed 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
     AssemblyCulture
    -0.93
    awtextra
    -0.91
    Personendaten
    -0.78
    FormTagHelper
    -0.75
    ⓧ
    -0.73
    LabelTagHelper
    -0.69
    twimg
    -0.68
    StandardCharsets
    -0.65
    astify
    -0.63
    WireFormat
    -0.63
    POSITIVE LOGITS
    getChildren
    0.50
     sequels
    0.49
    usda
    0.48
     grafts
    0.48
     escra
    0.47
     graft
    0.46
     progeny
    0.45
    ness
    0.45
    HomeAsUpEnabled
    0.45
     pups
    0.44
    Activations Density 0.763%

    No Known Activations