© 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. 5541
    Prev
    Next
    INDEX
    Explanations

    descriptions

    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
    AccessorTable
    -0.63
    ymce
    -0.57
     StatelessWidget
    -0.55
    ISupport
    -0.53
     numberWith
    -0.52
     وتسجيلات
    -0.50
    ]='\
    -0.50
    FactoryBean
    -0.49
    )_/¯
    -0.49
     onCancelled
    -0.49
    POSITIVE LOGITS
     CreateTagHelper
    0.60
    Includes
    0.58
    Proven
    0.57
     elicit
    0.56
    includes
    0.56
    msgSender
    0.56
    Tikang
    0.56
     provoked
    0.54
    Incluye
    0.54
    WillAppear
    0.53
    Activations Density 0.002%

    No Known Activations