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. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14171
    Prev
    Next
    INDEX
    Explanations

    words and phrases about biological or ecological relationships and tradeoffs

    oai_token-act-pair · gemini-2.0-flash

    off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/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
    setContentView
    -0.53
    FirebaseDatabase
    -0.50
     rette
    -0.49
     convenable
    -0.47
     actitudes
    -0.45
     correcto
    -0.45
     corretto
    -0.45
     présentés
    -0.43
    콘
    -0.43
     estrellas
    -0.42
    POSITIVE LOGITS
     >=",
    0.83
    الحياه
    0.78
     kasarigan
    0.77
     يتيمه
    0.75
    ьаж
    0.73
    ValueGeneration
    0.71
     unanswered
    0.69
     disponibilités
    0.69
    Билгалдахарш
    0.67
    OGND
    0.67
    Activations Density 2.721%

    No Known Activations