© 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. 2810
    Prev
    Next
    INDEX
    Explanations

    references to the physical location of objects, specifically the "floor."

    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
     OMIT
    -0.66
    eratops
    -0.62
    libft
    -0.60
    resultCode
    -0.60
     constexpr
    -0.57
    delwed
    -0.56
    :+:
    -0.56
    mäß
    -0.55
     Metab
    -0.55
     Roskov
    -0.55
    POSITIVE LOGITS
     floor
    3.88
     Floor
    3.52
    floor
    3.27
    Floor
    3.25
     FLOOR
    3.22
     floors
    3.03
    FLOOR
    2.80
     Floors
    2.63
    floors
    2.33
     flooring
    2.19
    Activations Density 0.011%

    No Known Activations