© 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. 10555
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Paul."

    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
    Negative Logits
     Anſ
    -1.17
     pleaſure
    -1.10
     Monfieur
    -1.05
     Reſ
    -1.02
     Diſ
    -0.99
     Theſe
    -0.98
     iſt
    -0.97
     ſy
    -0.97
     Houſe
    -0.96
     ſta
    -0.94
    POSITIVE LOGITS
     Paul
    1.57
    Paul
    1.34
     Paulson
    1.30
     PAUL
    1.20
     Paulus
    1.13
    PAUL
    1.12
     Paulina
    1.06
     paul
    1.01
    paul
    1.00
     Paula
    0.96
    Activations Density 0.005%

    No Known Activations