© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5830
    Prev
    Next
    INDEX
    Explanations

    references to Catholic churches, institutions, or religious sites

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     linkovi
    -0.68
    stylers
    -0.65
     defaultstate
    -0.63
    extAlignment
    -0.61
     bson
    -0.60
     monomers
    -0.60
    ValueStyle
    -0.60
    errHandler
    -0.59
     monomer
    -0.59
    AndroidJUnit
    -0.59
    POSITIVE LOGITS
     Catholic
    2.83
    Catholic
    2.55
     Catholics
    2.38
     catholic
    2.30
    catholic
    2.08
     Catholicism
    1.84
     CATH
    1.83
     catto
    1.75
     katholischen
    1.54
     católica
    1.52
    Activations Density 0.002%

    No Known Activations