© 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. 0-CLT-HP
    7. 45462
    Prev
    Next
    INDEX
    Explanations

    neonatal

    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
    -1.16
     שוליים
    -1.11
    tvguidetime
    -1.09
     createState
    -1.00
     للمعارف
    -1.00
     CreateTagHelper
    -1.00
    CloseOperation
    -0.96
    ształ
    -0.96
     Мексичка
    -0.96
     متعلقه
    -0.96
    POSITIVE LOGITS
     of
    0.56
     
    0.56
    .
    0.54
    os
    0.53
    ↵↵
    0.52
    ian
    0.50
     panel
    0.50
    <eos>
    0.50
     present
    0.50
    ish
    0.49
    Activations Density 0.204%

    No Known Activations