© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1059
    Prev
    Next
    INDEX
    Explanations

    words that could be German or Scandanavian

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.88
     disambiguazione
    -0.82
    føring
    -0.73
     مشين
    -0.71
     houſe
    -0.70
    hålla
    -0.70
     propOrder
    -0.70
    forChild
    -0.68
    bootstrapcdn
    -0.66
     препратки
    -0.63
    POSITIVE LOGITS
     het
    1.23
     det
    1.20
     Het
    1.05
    Het
    1.00
    Det
    0.93
     Det
    0.90
     sich
    0.88
     das
    0.87
     den
    0.84
     der
    0.82
    Activations Density 0.194%

    No Known Activations