© 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. 26564
    Prev
    Next
    INDEX
    Explanations

    geographical 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
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -1.11
     themſelves
    -0.90
     himſelf
    -0.89
     Sando
    -0.78
     Monfieur
    -0.78
     Abbe
    -0.77
     Erwin
    -0.77
     Betracht
    -0.77
     myſelf
    -0.77
     itſelf
    -0.77
    POSITIVE LOGITS
     Baltimore
    1.07
    Baltimore
    1.05
     Maryland
    0.97
    Maryland
    0.96
     Ravens
    0.88
    TIMORE
    0.80
     Orioles
    0.77
     Annapolis
    0.60
    Legături
    0.58
    "])){
    0.57
    Activations Density 0.236%

    No Known Activations