© 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. 28622
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations or water bodies specifically identified as "bay."

    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
     Evansville
    -0.84
     Manus
    -0.81
     Widodo
    -0.81
     againſt
    -0.80
     obfer
    -0.80
     itſelf
    -0.79
     mergeFrom
    -0.79
     Wraith
    -0.79
     Ugandan
    -0.78
     whoſe
    -0.78
    POSITIVE LOGITS
     Bay
    1.55
    Bay
    1.40
     BAY
    1.39
    BAY
    1.35
    bay
    1.30
     bay
    1.27
     bays
    1.15
     Bays
    1.01
     Bayley
    0.88
     bahía
    0.85
    Activations Density 0.012%

    No Known Activations