© 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. 1598
    Prev
    Next
    INDEX
    Explanations

    pocket

    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
     South
    -1.19
    South
    -0.86
     
    -0.78
     pocket
    -0.68
     SOUTH
    -0.67
     S
    -0.66
    ↵↵
    -0.65
    ↵
    -0.65
     (
    -0.65
     a
    -0.64
    POSITIVE LOGITS
     myſelf
    1.09
    ſelves
    1.07
    ArrowToggle
    1.06
    rillation
    1.02
     AspNetCore
    1.02
     متعلقه
    1.02
     Majefty
    1.00
     photolibrary
    0.99
     itſelf
    0.99
    ſelf
    0.98
    Activations Density 0.390%

    No Known Activations