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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1576
    Prev
    Next
    INDEX
    Explanations

    phrases containing "and" related to institutions such as government agencies and accredited university departments.

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
    .”)
    -0.79
    "),
    -0.78
    ?",
    -0.75
    ”),
    -0.75
     CreateTagHelper
    -0.75
    ?")
    -0.74
    ?”,
    -0.72
    —"
    -0.72
    —“
    -0.72
    LookAnd
    -0.71
    POSITIVE LOGITS
     vostri
    0.52
    empat
    0.49
     säll
    0.48
    corrência
    0.45
     betrek
    0.45
    ampilkan
    0.45
     vård
    0.44
    eseorang
    0.44
    zaamheid
    0.44
     träd
    0.43
    Activations Density 8.462%

    No Known Activations