© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12093
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    np_max-act · 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
     Réponses
    -0.59
     romantis
    -0.57
     Wiktionnaire
    -0.56
    Життєпис
    -0.55
    awtextra
    -0.54
     للمعارف
    -0.54
     estimés
    -0.53
     propOrder
    -0.53
     benefactor
    -0.51
     Lokales
    -0.50
    POSITIVE LOGITS
     оригіналу
    0.63
    __((
    0.60
    XmlAccessType
    0.54
    SizeMode
    0.52
     MSI
    0.51
     EINVAL
    0.50
    contentLoaded
    0.49
     SH
    0.49
    MLLoader
    0.49
    éril
    0.48
    Activations Density 0.071%

    No Known Activations