© 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. 5-CLT-HP
    7. 93787
    Prev
    Next
    INDEX
    Explanations

    interviews and quotes

    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
    expandindo
    -0.65
     tetanus
    -0.63
    theless
    -0.63
    TagHelper
    -0.62
    AutoScale
    -0.61
     Centi
    -0.60
    parametrize
    -0.58
    manship
    -0.58
    EditPart
    -0.57
    msgTypes
    -0.57
    POSITIVE LOGITS
     autorytatywna
    0.49
    شهاد
    0.48
     isInitialized
    0.47
     affid
    0.47
     thiệu
    0.44
    ämään
    0.43
     StatefulWidget
    0.43
     began
    0.42
    anglès
    0.42
    ]=>
    0.40
    Activations Density 0.010%

    No Known Activations