© 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. 22-RES-MATRYOSHKA-DC
    7. 3286
    Prev
    Next
    INDEX
    Explanations

    references to Christianity and specific dates or time periods

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     God
    -0.63
    styleType
    -0.60
     godly
    -0.54
     god
    -0.53
    God
    -0.53
    bitol
    -0.52
     &___
    -0.52
     Italijanski
    -0.51
    PCell
    -0.50
    ̍
    -0.50
    POSITIVE LOGITS
     Jesus
    0.76
    Jesus
    0.66
     SEDS
    0.59
     Galilee
    0.56
     Jesús
    0.56
     Magdalene
    0.56
     Yesus
    0.55
     jesus
    0.55
    ⓧ
    0.54
    Clik
    0.54
    Activations Density 0.090%

    No Known Activations