© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1697
    Prev
    Next
    INDEX
    Explanations

    words in Danish, specifically common words and the ends of words

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     samarbeid
    -0.73
     kveld
    -0.68
     utford
    -0.66
    følgelig
    -0.65
    nictví
    -0.63
     spørsmål
    -0.62
     spørs
    -0.62
     Roskov
    -0.60
     estimés
    -0.60
    skapet
    -0.59
    POSITIVE LOGITS
     Derfor
    0.58
    Ø
    0.58
     Copenhagen
    0.57
     Sø
    0.57
     Ø
    0.56
     Præ
    0.56
     til
    0.54
     Morten
    0.53
     Christians
    0.52
     Danish
    0.51
    Activations Density 0.493%

    No Known Activations