© 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. 91552
    Prev
    Next
    INDEX
    Explanations

    prey

    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
     their
    -0.64
     themselves
    -0.61
     ihre
    -0.54
     kanilang
    -0.50
    their
    -0.49
     ihrer
    -0.48
     ihren
    -0.48
    Their
    -0.48
     своего
    -0.46
    HStack
    -0.46
    POSITIVE LOGITS
    AddTagHelper
    0.77
    setVerticalGroup
    0.76
    '])){
    0.69
    CodeAttribute
    0.69
    ']))
    0.68
    StoryboardSegue
    0.68
    }}],
    0.65
    "]);
    0.65
    __(/*!
    0.64
    migrationBuilder
    0.63
    Activations Density 0.003%

    No Known Activations