© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75133
    Prev
    Next
    INDEX
    Explanations

    Code, documents, reviews

    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
     portátiles
    -0.49
    OHN
    -0.48
     χρόν
    -0.48
     régionale
    -0.48
     nastro
    -0.47
    addCriterion
    -0.47
     Tinker
    -0.47
     ldc
    -0.46
    <tfoot>
    -0.46
    nul
    -0.46
    POSITIVE LOGITS
     CreateTagHelper
    0.65
     initComponents
    0.60
    tagHelperRunner
    0.60
    ChildScrollView
    0.57
    Hozzáférés
    0.54
    UVWXYZ
    0.54
     pint
    0.54
    ViewInit
    0.54
     tongue
    0.51
    ISING
    0.50
    Activations Density 0.000%

    No Known Activations