© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30321
    Prev
    Next
    INDEX
    Explanations

    references to "crown" in various contexts, indicating a focus on royalty or authority

    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
     Pyle
    -0.78
    leg
    -0.77
    g
    -0.74
     fact
    -0.73
     Meier
    -0.73
     McGuire
    -0.72
     IANS
    -0.66
     Isi
    -0.66
     fato
    -0.66
    tti
    -0.66
    POSITIVE LOGITS
     Crowns
    1.49
     crowns
    1.42
     CROWN
    1.36
     Crown
    1.34
     crown
    1.33
    crown
    1.24
    Crown
    1.20
    crowned
    1.16
    NameInMap
    0.95
     couronne
    0.94
    Activations Density 0.004%

    No Known Activations