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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74399
    Prev
    Next
    INDEX
    Explanations

    ampersand

    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
    Identyfik
    -0.63
     vicenda
    -0.62
     الحره
    -0.60
     sauvages
    -0.60
     Exactos
    -0.60
    зулта
    -0.59
    MLLoader
    -0.59
     initComponents
    -0.59
     chi̍t
    -0.57
    存于互联网档案馆
    -0.56
    POSITIVE LOGITS
    &-
    0.72
     n
    0.71
    &
    0.70
     &
    0.68
     And
    0.66
    -&
    0.64
    &_
    0.63
    \&
    0.57
     [&
    0.57
    앤
    0.57
    Activations Density 0.000%

    No Known Activations