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. 31328
    Prev
    Next
    INDEX
    Explanations

    text within quotation marks, specifically single quotes that might suggest sarcasm or a certain viewpoint along with double quotes

    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
     <<<<<<<<<<<<<<
    -0.71
    InvalidProtocol
    -0.70
     ***!
    -0.69
     imdb
    -0.67
     avoient
    -0.66
     Europeo
    -0.66
     Popis
    -0.65
     canadien
    -0.63
     Batal
    -0.61
     AssemblyTitle
    -0.61
    POSITIVE LOGITS
    ViewFeatures
    0.59
    lolo
    0.58
    nadequate
    0.55
     propOrder
    0.52
    jones
    0.52
    kenstock
    0.51
    dega
    0.51
    สึก
    0.49
    》。
    0.49
    émoc
    0.48
    Activations Density 0.026%

    No Known Activations