© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91557
    Prev
    Next
    INDEX
    Explanations

    questions or requests for help

    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
     betweenstory
    -0.90
    InvalidProtocol
    -0.81
    RegressionTest
    -0.74
    TagMode
    -0.70
     ویکی‌پدیا
    -0.69
    tagHelperRunner
    -0.67
    Зноскі
    -0.67
     referenties
    -0.66
    AddTagHelper
    -0.66
    Hentet
    -0.65
    POSITIVE LOGITS
    cstdio
    0.50
    
    0.47
     pro
    0.45
     ListTile
    0.44
     prior
    0.44
    你也
    0.44
    icus
    0.43
    тьяна
    0.42
    onas
    0.41
    ToBounds
    0.41
    Activations Density 0.014%

    No Known Activations