© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13874
    Prev
    Next
    INDEX
    Explanations

    references to specific fashion magazine brands

    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
     ujednoznacz
    -0.68
     >=",
    -0.65
     transférez
    -0.58
    يكب
    -0.58
     المعرف
    -0.57
     utafitiHapana
    -0.55
    #+#
    -0.54
    jspx
    -0.51
     competition
    -0.50
     Competition
    -0.50
    POSITIVE LOGITS
    GQ
    3.77
     GQ
    2.70
     Vogue
    1.32
    Vogue
    1.24
    gq
    1.23
    vogue
    0.96
     Esquire
    0.80
     Cosmopolitan
    0.79
     vogue
    0.76
     Glamour
    0.66
    Activations Density 0.001%

    No Known Activations