© 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. 91434
    Prev
    Next
    INDEX
    Explanations

    Conversational speech fragments

    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
    \|^{
    -0.49
     peman
    -0.49
     Ведь
    -0.47
     cận
    -0.47
     Sart
    -0.47
    assume
    -0.46
     chứng
    -0.46
    odine
    -0.45
    AddComponent
    -0.44
    也沒
    -0.44
    POSITIVE LOGITS
    XmlAccessType
    0.89
    InjectAttribute
    0.79
    URLException
    0.66
    complexType
    0.66
     jScrollPane
    0.65
    typeorm
    0.62
    MessageOf
    0.61
    ImageContext
    0.61
    lapsingToolbar
    0.61
     فريبيس
    0.61
    Activations Density 0.006%

    No Known Activations