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. 14003
    Prev
    Next
    INDEX
    Explanations

    the word "vary" and its variants.

    oai_token-act-pair · gemini-2.0-flash

    vary

    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
    enumi
    -0.74
     متعلقه
    -0.73
     pinulongan
    -0.71
     esternos
    -0.67
    BeginInit
    -0.66
     '\\;'
    -0.65
     myſelf
    -0.65
     للاسماء
    -0.64
    HomeAsUpEnabled
    -0.64
    ]--;
    -0.62
    POSITIVE LOGITS
    writeField
    0.54
    trim
    0.43
     defStyle
    0.43
     ArrayAdapter
    0.43
     trim
    0.40
    EventLoop
    0.39
     JTextArea
    0.39
    RestController
    0.39
    Gizmos
    0.39
     Salle
    0.38
    Activations Density 0.985%

    No Known Activations