© 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. 12-RES-MATRYOSHKA-DC
    7. 12350
    Prev
    Next
    INDEX
    Explanations

    terms related to priests and the priesthood

    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
    apor
    -0.81
    ...>
    -0.70
     Taka
    -0.70
     ?...
    -0.70
    ably
    -0.69
     Haga
    -0.69
     Lucinda
    -0.69
    ==",
    -0.68
     Betts
    -0.68
    Luc
    -0.68
    POSITIVE LOGITS
     Priest
    1.55
     Priests
    1.53
     priests
    1.43
    priest
    1.35
    Priest
    1.34
     priest
    1.28
     Priester
    1.11
     sacerdote
    1.10
     priestly
    1.00
     PRI
    0.95
    Activations Density 0.001%

    No Known Activations