© 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. 23130
    Prev
    Next
    INDEX
    Explanations

    terms related to faith and belief systems

    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
    </i>
    -0.79
    ❤️❤️
    -0.71
    </b>
    -0.69
    ette
    -0.64
     ras
    -0.62
    stva
    -0.62
    NETT
    -0.61
    <i>
    -0.60
    hip
    -0.60
     Sylvie
    -0.60
    POSITIVE LOGITS
     FAITH
    1.51
     Faith
    1.41
    faith
    1.34
    Faith
    1.31
     faiths
    1.27
     faith
    1.22
     Faithful
    1.01
    SequentialGroup
    0.95
    XmlAccessorType
    0.92
     Waray
    0.92
    Activations Density 0.005%

    No Known Activations