© 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. 6747
    Prev
    Next
    INDEX
    Explanations

    references to specific network request types

    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
    oner
    -0.68
    oda
    -0.61
    enumi
    -0.59
     Ching
    -0.57
    ODA
    -0.56
    ägg
    -0.55
    TypeString
    -0.55
    吝
    -0.54
    blend
    -0.54
    راحل
    -0.54
    POSITIVE LOGITS
    req
    2.55
     req
    2.06
    Req
    1.50
    REQ
    1.37
     Req
    1.33
    reqs
    1.22
     REQ
    1.20
    ViewFeatures
    0.76
     hatchet
    0.74
     circumcision
    0.74
    Activations Density 0.004%

    No Known Activations