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. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16328
    Prev
    Next
    INDEX
    Explanations

    the word "idea" or nearby words related to concepts and thought

    oai_token-act-pair · gemini-2.0-flash

    idea

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/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
     OnInit
    -0.50
     vulgaires
    -0.48
    venidos
    -0.46
     auto
    -0.42
     AA
    -0.41
     personal
    -0.40
    Ibid
    -0.40
    WaitGroup
    -0.39
    ch
    -0.39
     long
    -0.39
    POSITIVE LOGITS
    StructEnd
    0.83
    mybatisplus
    0.80
    CloseOperation
    0.73
    osoba
    0.69
    XmlAccessType
    0.65
     typelib
    0.65
    WireFormatLite
    0.65
    DotNetBar
    0.65
    aarrggbb
    0.65
     Inflate
    0.64
    Activations Density 1.865%

    No Known Activations