© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74730
    Prev
    Next
    INDEX
    Explanations

    bound

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -2.09
     να
    -0.71
     anzu
    -0.70
    to
    -0.69
    到
    -0.67
    BeginContext
    -0.65
     einzu
    -0.62
    tobe
    -0.59
    DataTo
    -0.59
     einz
    -0.58
    POSITIVE LOGITS
    はじめに
    0.67
    NameInMap
    0.55
    TacToe
    0.54
    awtextra
    0.53
    Referințe
    0.53
     Gazetteer
    0.53
     дописавши
    0.53
     <>",
    0.52
     kasarigan
    0.50
    ParallelGroup
    0.49
    Activations Density 0.002%

    No Known Activations