© 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. 4-CLT-HP
    7. 986
    Prev
    Next
    INDEX
    Explanations

    user-generated text

    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
     vœux
    -0.61
     abiertos
    -0.58
     isolado
    -0.57
     recentes
    -0.57
     seuls
    -0.55
     preuves
    -0.54
     aberto
    -0.53
     producteurs
    -0.52
     leçons
    -0.52
     necessárias
    -0.52
    POSITIVE LOGITS
    mybatisplus
    0.71
     للمعارف
    0.67
     <<<<<<<<<<<<<<
    0.65
    igurumi
    0.64
    WebControls
    0.64
     different
    0.63
     >=",
    0.62
     uintptr
    0.61
    TagMode
    0.61
    RegressionTest
    0.61
    Activations Density 0.003%

    No Known Activations