© 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. 4862
    Prev
    Next
    INDEX
    Explanations

    references to hardware components and technical specifications related to system controllers, buses, and chips

    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
    UnitTesting
    -1.26
    enderror
    -0.95
    AndEndTag
    -0.94
     noDo
    -0.91
     Italijanski
    -0.89
    BagConstraints
    -0.88
     Picchu
    -0.87
    PostExecute
    -0.86
    يكب
    -0.85
     ―――――
    -0.85
    POSITIVE LOGITS
     Vorsch
    0.55
     
    0.51
     “
    0.48
     Lizenz
    0.48
    sdk
    0.47
    SDK
    0.46
     (
    0.45
     "
    0.44
     Go
    0.44
     so
    0.43
    Activations Density 1.063%

    No Known Activations