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. 1-CLT-HP
    4. 12329
    Prev
    Next
    INDEX
    Explanations

    see

    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
    ^(@)
    -0.68
     EconPapers
    -0.66
     itſelf
    -0.65
     martyrdom
    -0.64
    poptosis
    -0.60
     glandular
    -0.60
     ſeveral
    -0.59
     Agronomy
    -0.57
     neceff
    -0.57
     occaf
    -0.57
    POSITIVE LOGITS
     if
    0.65
     my
    0.60
     pic
    0.57
    ?$
    0.50
     which
    0.48
    ScopeManager
    0.47
    ?>"
    0.47
    ))){
    0.46
     Tip
    0.44
    )?
    0.44
    Activations Density 0.055%

    No Known Activations