© 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. 20493
    Prev
    Next
    INDEX
    Explanations

    statements regarding divine authority and worship-related concepts

    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
     Meksiku
    -0.56
    ódz
    -0.54
     lccn
    -0.54
    DataBind
    -0.50
    wapV
    -0.50
    NamedQuery
    -0.49
    ographies
    -0.48
    ff
    -0.48
    PhysRevD
    -0.48
     Sis
    -0.47
    POSITIVE LOGITS
     chré
    0.62
     calendriers
    0.62
     AttributeSet
    0.60
     réfugi
    0.60
     čierna
    0.60
     picioare
    0.59
     AssemblyTitle
    0.59
     חיצוניים
    0.58
     évêque
    0.58
     termica
    0.58
    Activations Density 0.007%

    No Known Activations