© 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. 77813
    Prev
    Next
    INDEX
    Explanations

    Court documents and articles

    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
    AndEndTag
    -0.69
    IntoConstraints
    -0.62
    DrawerToggle
    -0.57
    TacToe
    -0.57
    AddHtmlAttribute
    -0.49
    CppMethod
    -0.48
    Referanser
    -0.47
    UpInside
    -0.45
    BeginInit
    -0.45
     تانيه
    -0.44
    POSITIVE LOGITS
    ornos
    0.65
    Попис
    0.60
     coals
    0.59
     Silvio
    0.58
     Umbrella
    0.57
     capes
    0.57
    IUrlHelper
    0.57
     Mache
    0.57
     umbrellas
    0.56
     Conductor
    0.56
    Activations Density 0.005%

    No Known Activations