© 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. 23376
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ceremony" and related terms, indicating a focus on formal events and rituals

    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
    stateProvider
    -0.76
     credere
    -0.70
    doria
    -0.64
     Edison
    -0.60
     Estrella
    -0.58
     knap
    -0.58
    깥
    -0.58
    wia
    -0.57
     Ozone
    -0.57
     META
    -0.57
    POSITIVE LOGITS
     ceremony
    1.49
     Ritual
    1.46
     Ceremony
    1.41
     ceremonies
    1.36
     ritual
    1.35
    Ritual
    1.32
    ritual
    1.30
     rituals
    1.27
    emony
    1.19
     Ceremon
    1.17
    Activations Density 0.004%

    No Known Activations