© 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. 0-CLT-HP
    7. 44228
    Prev
    Next
    INDEX
    Explanations

    binding

    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
     createState
    -0.59
     Massen
    -0.55
    Билгалдахарш
    -0.50
    гиоз
    -0.50
     Kran
    -0.49
     Cranes
    -0.49
    oustics
    -0.48
     Servicing
    -0.48
     thiệu
    -0.47
     Crane
    -0.47
    POSITIVE LOGITS
     pinulongan
    0.74
    Hozzáférés
    0.63
     houſe
    0.58
    出版年
    0.58
     تضيفلها
    0.57
     AssemblyCulture
    0.56
     pleaſure
    0.54
    Gön
    0.51
     purpoſe
    0.51
    허
    0.50
    Activations Density 0.965%

    No Known Activations