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. 5-CLT-HP
    4. 95533
    Prev
    Next
    INDEX
    Explanations

    as

    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
     فريبيس
    -0.88
    MessageOf
    -0.79
    !*\
    -0.77
     initComponents
    -0.77
    RenderAtEndOf
    -0.71
     Chriftian
    -0.67
     насељу
    -0.67
     ſeveral
    -0.66
     Efq
    -0.65
    tonode
    -0.65
    POSITIVE LOGITS
     a
    0.99
     one
    0.75
     an
    0.67
     as
    0.60
     einem
    0.54
     einer
    0.51
     eine
    0.50
     sebagai
    0.49
     eines
    0.49
     maît
    0.48
    Activations Density 0.005%

    No Known Activations