© 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. 72564
    Prev
    Next
    INDEX
    Explanations

    Code and 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
     Waray
    -0.47
    InputBorder
    -0.45
    ImageField
    -0.43
    ::::::::
    -0.42
     Diri
    -0.42
     createSprite
    -0.41
    ніципалі
    -0.41
    DateField
    -0.41
    tec
    -0.41
    Clik
    -0.40
    POSITIVE LOGITS
     AssemblyCompany
    0.64
    XmlAccessorType
    0.61
    IsPostBack
    0.60
     defaultstate
    0.60
    تقاوى
    0.59
    ̍t
    0.58
     onBind
    0.57
    jsonwebtoken
    0.56
    पया
    0.56
    richTextPanel
    0.55
    Activations Density 0.006%

    No Known Activations