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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 31024
    Prev
    Next
    INDEX
    Explanations

    the word "such" in a mathematical context

    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
     >=",
    -0.77
    MessageTagHelper
    -0.66
    GEBURTSDATUM
    -0.64
    serviceWorker
    -0.63
     betweenstory
    -0.61
    ">$
    -0.60
     porcelaine
    -0.60
     AssemblyCulture
    -0.60
     Obtén
    -0.59
    AndEndTag
    -0.58
    POSITIVE LOGITS
    űr
    0.57
     sure
    0.56
     haplo
    0.56
    Dare
    0.53
    шое
    0.53
    tanooga
    0.53
     reason
    0.52
     alibi
    0.52
     Harg
    0.52
     Means
    0.51
    Activations Density 0.011%

    No Known Activations