© 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. 20760
    Prev
    Next
    INDEX
    Explanations

    references to a specific name or entity, particularly "Clark"

    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
     يتيمه
    -1.24
    ollectionView
    -0.88
    InputBorder
    -0.82
    *************
    -0.78
     Pote
    -0.77
    ので
    -0.75
    ^(@)
    -0.74
     Ugo
    -0.74
     basi
    -0.73
    anueva
    -0.73
    POSITIVE LOGITS
     Clark
    1.69
     CLARK
    1.53
    Clark
    1.47
     clark
    1.38
    clark
    1.33
     Clarks
    1.20
     Clarke
    1.08
    lark
    0.96
    Clarke
    0.87
     Hark
    0.80
    Activations Density 0.003%

    No Known Activations