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. 0-CLT-HP
    4. 91758
    Prev
    Next
    INDEX
    Explanations

    How

    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
     Majefty
    -0.80
     CreateTagHelper
    -0.78
     defaultstate
    -0.74
     poffe
    -0.74
     تضيفلها
    -0.73
     Monfieur
    -0.73
     perfons
    -0.71
     Jefus
    -0.69
     Efq
    -0.64
     themſelves
    -0.63
    POSITIVE LOGITS
     to
    0.90
     I
    0.70
    to
    0.68
     i
    0.60
     To
    0.55
    -
    0.54
    '
    0.54
     it
    0.51
     you
    0.51
     would
    0.51
    Activations Density 0.415%

    No Known Activations