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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14166
    Prev
    Next
    INDEX
    Explanations

    descriptions of time, mainly days or nights, sometimes using the word "following" or "next."

    oai_token-act-pair · gemini-2.0-flash

    next the following

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/width_16k
    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
     daquele
    -1.16
     naquele
    -1.14
    Ese
    -1.09
     ese
    -1.06
    那個
    -1.05
    quela
    -1.03
     Ese
    -1.01
    那个
    -0.99
    THAT
    -0.98
     esa
    -0.96
    POSITIVE LOGITS
    今年
    0.42
     summer
    0.39
    Erstellt
    0.39
     Thursday
    0.38
     Monday
    0.37
     year
    0.36
    Thursday
    0.35
     הע
    0.35
     today
    0.34
    ugian
    0.34
    Activations Density 0.560%

    No Known Activations