© 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. 1-RES-MATRYOSHKA-DC
    7. 799
    Prev
    Next
    INDEX
    Explanations

    references to spatial proximity or location descriptors

    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
     Cir
    -1.22
     Circle
    -1.12
    Cir
    -1.11
    circle
    -1.08
     circle
    -1.07
     ring
    -1.04
    Circle
    -0.99
     Circular
    -0.99
    cir
    -0.98
    ring
    -0.97
    POSITIVE LOGITS
     around
    3.94
     Around
    3.61
    Around
    3.61
    around
    3.55
     AROUND
    3.36
    AROUND
    2.89
     alrededor
    2.80
     autour
    2.52
     rundt
    2.39
     intorno
    2.28
    Activations Density 0.053%

    No Known Activations