© 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. 5917
    Prev
    Next
    INDEX
    Explanations

    references to contextual understanding or information sources

    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
    PERTY
    -0.54
     estimés
    -0.54
    帖最后由
    -0.51
    Hrsg
    -0.48
    googleapis
    -0.48
    posite
    -0.48
     context
    -0.47
     arşivlendi
    -0.47
     medel
    -0.47
    合
    -0.46
    POSITIVE LOGITS
    Context
    2.20
     Context
    1.04
    thodon
    0.81
     AssemblyCompany
    0.77
    Contexto
    0.66
    yntaxException
    0.65
    
    0.63
     fût
    0.63
    CONTEXT
    0.62
     typelib
    0.60
    Activations Density 0.006%

    No Known Activations