© 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. 5094
    Prev
    Next
    INDEX
    Explanations

    references to hep-preprint identifiers

    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
     CreateTagHelper
    -0.85
    évaluateur
    -0.82
     noDo
    -0.82
     Meksiku
    -0.79
     Winaray
    -0.79
    PYX
    -0.76
    MemoryWarning
    -0.75
     ChromeDriver
    -0.74
    Демографія
    -0.73
    المناصب
    -0.73
    POSITIVE LOGITS
    hep
    2.97
     hep
    1.94
    Hep
    1.73
     Hep
    1.68
    HEP
    1.64
     HEP
    1.29
     hepatitis
    0.78
     Hepatitis
    0.77
     hepat
    0.62
     Hepburn
    0.60
    Activations Density 0.008%

    No Known Activations