© 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. 90667
    Prev
    Next
    INDEX
    Explanations

    pneumatic

    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
     itſelf
    -0.99
    ه
    -0.99
     myſelf
    -0.98
     houſe
    -0.97
     purpoſe
    -0.97
     pleaſure
    -0.96
     PLW
    -0.95
     Phoen
    -0.94
     للمعارف
    -0.93
     poffible
    -0.92
    POSITIVE LOGITS
     le
    0.50
     former
    0.49
     
    0.46
     con
    0.45
     "
    0.45
     ir
    0.45
     latter
    0.43
     ther
    0.43
    <h1>
    0.42
     el
    0.42
    Activations Density 1.607%

    No Known Activations