© 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. 32334
    Prev
    Next
    INDEX
    Explanations

    references to God and discussions of faith, particularly in the context of religious beliefs and criticism of capitalism

    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
    ">—
    -0.52
    TagMode
    -0.50
    ServletRequest
    -0.49
    <![
    -0.48
    #+#
    -0.47
    ASER
    -0.47
    prava
    -0.46
     cutting
    -0.45
    
    -0.45
    jaer
    -0.45
    POSITIVE LOGITS
    ArrowToggle
    0.66
     propOrder
    0.65
    psack
    0.64
    HostException
    0.63
    intios
    0.61
    ftagPool
    0.60
     gainera
    0.59
    poptotic
    0.57
     الحره
    0.57
    oredCriteria
    0.56
    Activations Density 0.022%

    No Known Activations