© 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. 2825
    Prev
    Next
    INDEX
    Explanations

    references to shopping activities or locations

    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
     firebaseConfig
    -0.59
    philis
    -0.58
    .*")]
    -0.58
     Minato
    -0.58
     univ
    -0.57
     Lure
    -0.57
    Grant
    -0.56
     Grant
    -0.55
     cbr
    -0.55
    gdala
    -0.54
    POSITIVE LOGITS
     shop
    3.47
     Shop
    3.30
     SHOP
    3.22
    Shop
    3.16
    shop
    3.11
    SHOP
    3.03
     shops
    2.86
     Shops
    2.78
    shops
    2.64
     shopping
    2.45
    Activations Density 0.052%

    No Known Activations