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. 16685
    Prev
    Next
    INDEX
    Explanations

    XML code with the tag "item."

    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
    ostante
    -0.71
    li
    -0.63
    paravant
    -0.62
    WebServlet
    -0.61
    ніципалі
    -0.59
     Scand
    -0.59
     pleaſure
    -0.58
     disambiguazione
    -0.58
    Bli
    -0.57
     Rossetti
    -0.57
    POSITIVE LOGITS
    DoubleQuotes
    0.87
     تانيه
    0.66
    WriteAttribute
    0.65
    ImageContext
    0.60
    unhofer
    0.58
    άζ
    0.55
    ITUTE
    0.52
    UnknownFields
    0.52
    GIUM
    0.52
    וות
    0.52
    Activations Density 0.001%

    No Known Activations