© 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. 91997
    Prev
    Next
    INDEX
    Explanations

    technical information

    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
     themſelves
    -0.75
    ſelves
    -0.73
     ostavi
    -0.72
    tanleria
    -0.70
     raiſ
    -0.69
     itſelf
    -0.69
    ItemBackground
    -0.69
    adays
    -0.68
     Roskov
    -0.68
     externi
    -0.66
    POSITIVE LOGITS
     chủ
    0.52
    宿
    0.50
     QName
    0.50
     avan
    0.49
     suis
    0.49
    KEYCODE
    0.47
     skj
    0.47
     public
    0.46
     rest
    0.46
    IMPORTED
    0.46
    Activations Density 1.177%

    No Known Activations