© 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. 32405
    Prev
    Next
    INDEX
    Explanations

    terms related to historical territories and political changes in Denmark and Schleswig-Holstein

    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
    AddTagHelper
    -1.09
     nakalista
    -1.04
    "];
    -0.96
     سكانية
    -0.94
    Vendo
    -0.89
     gainera
    -0.88
    CardHeader
    -0.88
    المشاركات
    -0.87
    öbb
    -0.86
    )}
    -0.85
    POSITIVE LOGITS
    ly
    0.87
    teen
    0.83
     figliu
    0.82
     pleaſure
    0.80
     diſt
    0.77
     innamor
    0.76
     perſon
    0.75
     deſt
    0.75
     ejus
    0.74
     sostitu
    0.73
    Activations Density 1.162%

    No Known Activations