© 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. 520
    Prev
    Next
    INDEX
    Explanations

    words and phrases pertaining to religion and personal values

    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
    #+#
    -0.75
    verifyException
    -0.63
    ChildScrollView
    -0.60
    ScopeManager
    -0.58
    GEBURTSDATUM
    -0.57
    coroutines
    -0.55
    Predecesor
    -0.55
    layoutControl
    -0.55
     AssemblyProduct
    -0.54
    -------------</
    -0.54
    POSITIVE LOGITS
     religion
    1.45
     religious
    1.40
     religions
    1.30
     Religion
    1.27
    religion
    1.27
     faiths
    1.26
     Religious
    1.22
    religious
    1.20
     faith
    1.19
    Religious
    1.19
    Activations Density 1.294%

    No Known Activations