© 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. 11683
    Prev
    Next
    INDEX
    Explanations

    references to shrine-related entities

    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
     Cheddar
    -0.60
     Talley
    -0.60
     YAP
    -0.60
     الحره
    -0.57
    CppCodeGen
    -0.54
     Coleridge
    -0.54
     Beres
    -0.54
     NCT
    -0.53
    jspb
    -0.53
    reportWebVitals
    -0.53
    POSITIVE LOGITS
    Shr
    3.30
     Shr
    3.00
     Shrine
    2.69
    shr
    2.47
     shrine
    2.33
     shrines
    2.06
     shr
    1.66
     SHR
    1.46
     Shrub
    1.37
     shrub
    1.31
    Activations Density 0.002%

    No Known Activations