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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41867
    Prev
    Next
    INDEX
    Explanations

    globe

    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
     FormsModule
    -0.68
    IContainer
    -0.65
     globe
    -0.62
     ControllerBase
    -0.61
     Xunit
    -0.60
    >",
    -0.58
     StatefulWidget
    -0.58
     Suspension
    -0.57
     Curtain
    -0.57
     الوطنيه
    -0.56
    POSITIVE LOGITS
     Efq
    0.68
    __*/
    0.60
    ers
    0.59
    er
    0.57
     noires
    0.56
     natale
    0.54
     enfans
    0.54
    yards
    0.53
    house
    0.52
     picioare
    0.51
    Activations Density 0.121%

    No Known Activations