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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15518
    Prev
    Next
    INDEX
    Explanations

    references to the number or presence of a booth

    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
    unnitel
    -0.49
    発
    -0.48
     handle
    -0.47
    Jac
    -0.46
     Vanden
    -0.45
    weg
    -0.43
     respec
    -0.42
    ฏิ
    -0.42
    RUS
    -0.42
     Donaldson
    -0.42
    POSITIVE LOGITS
     booth
    4.06
     booths
    3.34
    booth
    3.14
     Booth
    3.09
    Booth
    3.09
    ブース
    1.87
     kiosk
    1.00
     cabina
    0.96
     stall
    0.92
     cubicle
    0.88
    Activations Density 0.001%

    No Known Activations