© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2345
    Prev
    Next
    INDEX
    Explanations

    purest

    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
    StoryboardSegue
    -0.78
    setVerticalGroup
    -0.72
    Rhestr
    -0.72
    expandindo
    -0.70
     الرياضيه
    -0.64
    Jîn
    -0.63
    المناصب
    -0.62
     تضيفلها
    -0.61
    AndEndTag
    -0.61
    الحياه
    -0.60
    POSITIVE LOGITS
     to
    0.55
     poti
    0.49
     point
    0.47
     experience
    0.47
     state
    0.46
    onSave
    0.46
    Occurred
    0.45
    tenths
    0.44
    PointerException
    0.44
     story
    0.43
    Activations Density 0.002%

    No Known Activations