© 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. 5-CLT-HP
    7. 706
    Prev
    Next
    INDEX
    Explanations

    code and technical language

    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
    NOPQRST
    -0.60
    SuppressMessage
    -0.55
    SEGUIR
    -0.46
    sok
    -0.44
    زالة
    -0.43
    fony
    -0.43
     préférable
    -0.42
     valeur
    -0.42
    PushMatrix
    -0.42
    لكتر
    -0.42
    POSITIVE LOGITS
    StoryboardSegue
    0.71
    featureID
    0.69
    LabelTagHelper
    0.66
    RTEX
    0.65
    webElementXpaths
    0.60
    :✨
    0.59
    aarrggbb
    0.57
     continúas
    0.56
    ert
    0.54
    NameInMap
    0.54
    Activations Density 0.001%

    No Known Activations