© 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. 31967
    Prev
    Next
    INDEX
    Explanations

    terms related to skepticism towards religious beliefs and affiliations

    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
    ʐ
    -0.63
    getOutputStream
    -0.57
    ścio
    -0.53
    esri
    -0.51
    CodeDom
    -0.50
    initComponents
    -0.50
    DllImport
    -0.50
     esenciales
    -0.49
    StoryboardSegue
    -0.49
     dignidad
    -0.49
    POSITIVE LOGITS
     Athe
    1.41
    Athe
    1.31
     atheist
    1.23
     atheism
    1.23
     atheists
    1.22
     Ske
    1.02
     skep
    1.01
     athe
    0.98
     scep
    0.97
    Ske
    0.92
    Activations Density 0.014%

    No Known Activations