© 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. 4-CLT-HP
    7. 607
    Prev
    Next
    INDEX
    Explanations

    get

    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
     in
    -0.44
    ̍
    -0.42
    up
    -0.41
    dyž
    -0.41
    стве
    -0.40
     on
    -0.40
     up
    -0.39
     from
    -0.39
     contente
    -0.39
    indexOf
    -0.38
    POSITIVE LOGITS
    StructEnd
    0.81
     Réponses
    0.77
     Roskov
    0.74
    Datuak
    0.71
    migrationBuilder
    0.70
    IUrlHelper
    0.69
     NDEBUG
    0.67
     AssemblyTitle
    0.67
     Mère
    0.66
     betweenstory
    0.64
    Activations Density 0.014%

    No Known Activations