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. 9-RES-MATRYOSHKA-DC
    4. 16604
    Prev
    Next
    INDEX
    Explanations

    the word "on"

    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
    ьаж
    -0.96
    IUrlHelper
    -0.90
     betweenstory
    -0.89
     ItemStack
    -0.88
    ]")]
    -0.86
    Хьажоргаш
    -0.85
     NSCoder
    -0.84
    Vidite
    -0.84
     GenerationType
    -0.81
    ItemBackground
    -0.80
    POSITIVE LOGITS
    codegen
    0.57
     लिया
    0.54
     bero
    0.49
     "__
    0.47
    vad
    0.46
    zik
    0.46
    这段
    0.46
    ORT
    0.45
    azine
    0.45
    zem
    0.44
    Activations Density 0.094%

    No Known Activations