© 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. 17145
    Prev
    Next
    INDEX
    Explanations

    geographic locations and place names

    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
     itſelf
    -0.94
     myſelf
    -0.89
     houſe
    -0.87
     Majefty
    -0.85
     ſever
    -0.81
     himſelf
    -0.80
    ंदीखरीदारी
    -0.79
     perſon
    -0.79
    AsUp
    -0.78
     ſame
    -0.77
    POSITIVE LOGITS
     G
    0.54
     hogy
    0.51
     RIP
    0.50
     Ernst
    0.48
    lag
    0.48
     Ben
    0.47
     Ros
    0.47
    帖最后由
    0.47
     Vill
    0.47
    laise
    0.47
    Activations Density 0.145%

    No Known Activations