© 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. 0-RES-MATRYOSHKA-DC
    7. 11518
    Prev
    Next
    INDEX
    Explanations

    references to a specific computational framework or methodology related to Triadic methods or systems

    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
     tr
    -0.55
     Joaquim
    -0.55
     tre
    -0.52
     tri
    -0.52
    WithIOException
    -0.49
     tra
    -0.49
     vol
    -0.46
    tra
    -0.46
     Eng
    -0.46
     miro
    -0.45
    POSITIVE LOGITS
    Tri
    1.98
     Tri
    1.95
     Trib
    1.05
     TRI
    0.93
     Tribun
    0.81
     TRIB
    0.79
     Три
    0.78
     Tribunal
    0.74
    存于互联网档案馆
    0.74
    يكب
    0.71
    Activations Density 0.001%

    No Known Activations