© 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. 20520
    Prev
    Next
    INDEX
    Explanations

    the mention of the word "Hall" in various contexts

    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
    wendi
    -0.86
     bê
    -0.84
     Zapata
    -0.78
    mels
    -0.77
    orderItem
    -0.77
     McCulloch
    -0.77
     Stel
    -0.74
     Agrico
    -0.74
     Mier
    -0.74
     hivat
    -0.73
    POSITIVE LOGITS
     Hall
    1.66
     hall
    1.63
     HALL
    1.50
     halls
    1.49
     Halls
    1.49
    Hall
    1.45
    hall
    1.40
    HALL
    1.40
     hallway
    1.05
     Haller
    0.94
    Activations Density 0.010%

    No Known Activations