© 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. 1-CLT-HP
    7. 9183
    Prev
    Next
    INDEX
    Explanations

    scientific experiments

    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
    ensation
    -0.55
    ();*/
    -0.50
    titution
    -0.49
    pyx
    -0.49
     '<?
    -0.48
    uming
    -0.48
    AMIENTO
    -0.48
    uary
    -0.48
    iser
    -0.48
    lets
    -0.47
    POSITIVE LOGITS
    fromnode
    0.71
     архивлан
    0.68
    MessageTagHelper
    0.63
    SpringBootTest
    0.63
    UnusedPrivate
    0.61
     незавершена
    0.60
    principalTable
    0.57
     saites
    0.57
    InjectAttribute
    0.57
     lignin
    0.57
    Activations Density 0.010%

    No Known Activations