Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14227
    Prev
    Next
    INDEX
    Explanations

    words and phrases possibly related to military conflict, titles, awards, and ranks

    oai_token-act-pair · 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
    AddTagHelper
    -0.68
    BeginContext
    -0.59
     Вікі
    -0.57
    BufferException
    -0.56
     sq
    -0.54
     насељу
    -0.54
    HideFlags
    -0.54
    lemish
    -0.54
     MonoBehaviour
    -0.53
    borderSide
    -0.52
    POSITIVE LOGITS
     متعلقه
    0.58
    QMetaType
    0.54
     estimés
    0.54
    olite
    0.52
     comment
    0.51
    entum
    0.50
     reflected
    0.49
    Naissance
    0.49
    ]=>
    0.48
    исленность
    0.48
    Activations Density 10.147%

    No Known Activations