© 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. 15036
    Prev
    Next
    INDEX
    Explanations

    references to the Pacific region

    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
    InputBorder
    -0.79
    verwijspagina
    -0.79
     DSA
    -0.76
    Referencias
    -0.74
    dieu
    -0.73
     protoimpl
    -0.72
    rungsseite
    -0.72
    پرد
    -0.72
    kaido
    -0.71
    hassee
    -0.71
    POSITIVE LOGITS
     PACIFIC
    1.29
     Pac
    1.24
     Pacific
    1.24
    pacific
    1.09
    Pacific
    1.08
    Pac
    1.02
     pacific
    1.02
    CEAN
    0.97
     Pacífico
    0.96
     PAC
    0.95
    Activations Density 0.010%

    No Known Activations