© 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. 72356
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    MigrationBuilder
    -0.71
     فريبيس
    -0.70
     мәкал
    -0.69
    yntaxException
    -0.62
    الحياه
    -0.61
    tagHelperRunner
    -0.61
    mbic
    -0.61
    хьтан
    -0.61
     незавершена
    -0.60
     Weyl
    -0.59
    POSITIVE LOGITS
    DebuggerNonUser
    0.55
     CreateTagHelper
    0.50
    PRF
    0.48
    uol
    0.47
     Right
    0.47
     ips
    0.42
    PageIndex
    0.42
     Out
    0.41
     pré
    0.40
    oluzione
    0.40
    Activations Density 0.000%

    No Known Activations