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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1366
    Prev
    Next
    INDEX
    Explanations

    text related to laws, catholicism, or religion

    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
    Not in Any Lists

    No Comments

    Negative Logits
     mapStateToProps
    -0.52
     Whig
    -0.51
    ModuleName
    -0.48
    WriteString
    -0.47
     Ahmet
    -0.45
    setOutput
    -0.45
     glider
    -0.44
    DispatchToProps
    -0.43
    iastes
    -0.43
     Herodotus
    -0.42
    POSITIVE LOGITS
     Pope
    1.13
     Catholic
    1.13
    Pope
    1.09
     Vatican
    1.08
    Catholic
    1.04
     pope
    1.01
     Catholics
    1.00
     Cardinal
    0.99
     catholic
    0.96
     diocese
    0.94
    Activations Density 0.748%

    No Known Activations