© 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. 23440
    Prev
    Next
    INDEX
    Explanations

    references to the Chan family and related entities

    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
     оригіналу
    -0.85
    __*/
    -0.84
     TPR
    -0.83
     }}"></
    -0.82
     Maier
    -0.81
     dataSnapshot
    -0.78
     createState
    -0.75
    ftagPool
    -0.74
     lenker
    -0.74
    WireFormatLite
    -0.73
    POSITIVE LOGITS
     Chan
    1.54
    Chan
    1.22
     chan
    1.13
     CHAN
    1.05
    CHAN
    0.94
     Chancery
    0.93
    chan
    0.91
     Channing
    0.87
     Chancellor
    0.82
     Chand
    0.81
    Activations Density 0.005%

    No Known Activations