Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 31346
    Prev
    Next
    INDEX
    Explanations

    language typical of claims in a patent specification.

    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
    apimachinery
    -0.67
    τευ
    -0.52
     indic
    -0.51
    ActivityCompat
    -0.51
    unar
    -0.49
    \}\\
    -0.49
    XmlAccessorType
    -0.47
    Zitat
    -0.46
    CONCURRENT
    -0.46
    fillType
    -0.45
    POSITIVE LOGITS
    setVerticalGroup
    0.81
    olism
    0.62
    مقاله
    0.59
     gynhyrchwyd
    0.58
    RenderAtEndOf
    0.57
     shack
    0.56
    شهاد
    0.56
     gawas
    0.55
     Akismet
    0.55
     transfieras
    0.54
    Activations Density 0.169%

    No Known Activations