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. 14125
    Prev
    Next
    INDEX
    Explanations

    the phrase "your smartphone"

    oai_token-act-pair · gemini-2.0-flash

    phones

    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
     EconPapers
    -0.73
     commerciaux
    -0.55
     commerciales
    -0.54
     juridiques
    -0.54
     hjem
    -0.54
     normaux
    -0.54
     magát
    -0.53
    sunter
    -0.52
     дописавши
    -0.52
     étrangères
    -0.50
    POSITIVE LOGITS
     smartphone
    1.52
     smartphones
    1.52
     phones
    1.49
     Smartphones
    1.47
     Smartphone
    1.45
     phone
    1.39
     Phones
    1.30
     cellphone
    1.30
    smartphone
    1.27
     iPhone
    1.25
    Activations Density 1.606%

    No Known Activations