© 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. 20-CLT-HP
    7. 77833
    Prev
    Next
    INDEX
    Explanations

    technical language

    np_max-act-logits · 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
     समीक्षाओं
    -0.57
    tagext
    -0.55
     ostavi
    -0.54
    piram
    -0.53
    intellij
    -0.53
    ┆
    -0.50
     lepid
    -0.49
     Obrador
    -0.48
    tonsoft
    -0.48
    ：“……”
    -0.47
    POSITIVE LOGITS
     depart
    0.65
    MessageTagHelper
    0.58
    FormTagHelper
    0.57
     distance
    0.56
     problem
    0.55
     qualify
    0.52
    PreExecute
    0.52
    HtmlAttribute
    0.51
     rece
    0.50
    เดิน
    0.49
    Activations Density 0.000%

    No Known Activations