© 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. 43953
    Prev
    Next
    INDEX
    Explanations

    Jedi

    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
    acids
    -0.63
     or
    -0.59
    i
    -0.53
     Jedi
    -0.52
    a
    -0.48
    b
    -0.46
     person
    -0.45
    c
    -0.45
    ’
    -0.44
    e
    -0.43
    POSITIVE LOGITS
     Monfieur
    0.98
    tagHelperRunner
    0.96
    MessageTagHelper
    0.95
     themſelves
    0.94
    tvguidetime
    0.91
     itſelf
    0.90
     Jefus
    0.89
     initComponents
    0.88
     ModelExpression
    0.88
     getItemId
    0.88
    Activations Density 1.663%

    No Known Activations