© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5402
    Prev
    Next
    INDEX
    Explanations

    references to naming conventions related to a standardized method or pattern

    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
    CardModule
    -0.56
    GetType
    -0.54
     Probably
    -0.52
    ductory
    -0.52
     mesurer
    -0.51
    andia
    -0.51
     Asturias
    -0.51
    carina
    -0.51
    ècie
    -0.50
     Sert
    -0.50
    POSITIVE LOGITS
     convention
    3.52
     Convention
    3.36
    Convention
    3.28
    convention
    3.06
     conventions
    2.94
     Conventions
    2.86
    Conven
    2.16
    conven
    1.98
    VENTION
    1.64
     Conven
    1.62
    Activations Density 0.005%

    No Known Activations