© 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. 30652
    Prev
    Next
    INDEX
    Explanations

    references to beliefs and their importance 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
     Hess
    -0.74
     Dillon
    -0.67
    printStackTrace
    -0.65
     locul
    -0.65
    amous
    -0.64
    maca
    -0.63
    domo
    -0.63
    loed
    -0.59
    enheim
    -0.59
    Anar
    -0.59
    POSITIVE LOGITS
     Beliefs
    0.97
     beliefs
    0.87
     Belief
    0.82
    belief
    0.81
    Belief
    0.81
    Smarty
    0.78
     Thought
    0.77
     ModelExpression
    0.75
     belief
    0.73
     myś
    0.73
    Activations Density 0.003%

    No Known Activations