© 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. 12-RES-MATRYOSHKA-DC
    7. 10267
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, particularly cities like Paris and Tokyo

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.63
    GeneratedValue
    -0.62
     impac
    -0.60
    "/></
    -0.59
     Roch
    -0.59
     Stande
    -0.58
    randomUUID
    -0.57
    borderSide
    -0.57
    szön
    -0.57
     estekak
    -0.56
    POSITIVE LOGITS
    riwal
    0.95
    lamabad
    0.94
     européennes
    0.91
     Kabul
    0.90
     DELHI
    0.90
     Moscow
    0.85
     paris
    0.83
     Parisi
    0.82
    thly
    0.81
     Tokyo
    0.79
    Activations Density 0.025%

    No Known Activations