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. 31244
    Prev
    Next
    INDEX
    Explanations

    mentions of safety ratings, alert levels and associated adverbs

    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
    UserScript
    -0.72
     Akismet
    -0.71
     Monfieur
    -0.70
    AccessorTable
    -0.69
     NSCoder
    -0.69
     itſelf
    -0.69
     onPostExecute
    -0.69
     lords
    -0.68
    Amicalement
    -0.65
     scania
    -0.65
    POSITIVE LOGITS
     code
    0.48
     certification
    0.48
     استنادى
    0.47
     higher
    0.45
     betweenstory
    0.45
     status
    0.45
     hạng
    0.44
     Code
    0.43
     FIG
    0.42
     “
    0.42
    Activations Density 0.089%

    No Known Activations