© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19567
    Prev
    Next
    INDEX
    Explanations

    mentions of religion, particularly in various contexts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Nichols
    -0.75
    sai
    -0.62
    வர்
    -0.61
    OutOfRange
    -0.61
    Tilt
    -0.60
     sucht
    -0.59
    sze
    -0.59
    ی
    -0.58
    {//
    -0.57
     toimi
    -0.57
    POSITIVE LOGITS
     itſelf
    1.27
     myſelf
    1.09
     Majefty
    1.04
     pleaſure
    1.02
     Jefus
    1.02
     fubject
    0.98
    theless
    0.97
     purpoſe
    0.96
     houſe
    0.95
     Efq
    0.90
    Activations Density 0.002%

    No Known Activations