© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 20978
    Prev
    Next
    INDEX
    Explanations

    references to Cambridge and related locations

    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
    Negative Logits
    NegativeButton
    -0.70
     №
    -0.66
    awtextra
    -0.66
    PositiveButton
    -0.63
     Prieto
    -0.63
    menuStrip
    -0.61
     Presley
    -0.60
    SPJ
    -0.60
     MacDonald
    -0.59
     Supers
    -0.59
    POSITIVE LOGITS
     Cambridge
    1.85
    Cambridge
    1.68
    ridgeshire
    1.01
     camb
    0.93
     Kame
    0.93
     Camb
    0.83
    BRIDGE
    0.80
    camb
    0.79
     CAM
    0.78
    Sagittarius
    0.77
    Activations Density 0.004%

    No Known Activations