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. 1635
    Prev
    Next
    INDEX
    Explanations

    words and phrases used to describe daily life

    oai_token-act-pair · gemini-2.0-flash

    busy

    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
     busy
    -2.89
     Busy
    -2.61
    busy
    -2.58
    Busy
    -2.44
     busiest
    -2.06
     sibuk
    -1.64
    BUSY
    -1.52
    忙
    -1.52
     ocupado
    -1.43
     occupé
    -1.42
    POSITIVE LOGITS
    INCREF
    0.50
     actionPerformed
    0.48
    ofollow
    0.46
    nesi
    0.44
    tubers
    0.44
    DetailView
    0.43
    isei
    0.43
    Flatten
    0.42
     Vries
    0.42
    vata
    0.42
    Activations Density 2.128%

    No Known Activations