© 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. 41352
    Prev
    Next
    INDEX
    Explanations

    adolescents

    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
     Express
    -0.77
     EXPRESS
    -0.72
     express
    -0.69
    Express
    -0.67
    MLLoader
    -0.58
    hex
    -0.57
    ارش
    -0.57
     expresses
    -0.56
     prévue
    -0.55
    reportWebVitals
    -0.55
    POSITIVE LOGITS
    einander
    0.63
    keted
    0.54
    protoimpl
    0.53
    epa
    0.52
    rofoam
    0.52
    itively
    0.51
    🏻‍♀️
    0.51
    ulated
    0.49
    uate
    0.48
    ویه
    0.47
    Activations Density 0.341%

    No Known Activations