© 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. 4-CLT-HP
    7. 2852
    Prev
    Next
    INDEX
    Explanations

    technical writing/code

    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
    ImageContext
    -0.75
    DockStyle
    -0.70
    évaluateur
    -0.62
    SharedCtor
    -0.62
    ":[{
    -0.61
    MessageTagHelper
    -0.59
    __(/*!
    -0.58
    CodeDom
    -0.58
    VersionUID
    -0.58
     дописавши
    -0.57
    POSITIVE LOGITS
     the
    0.78
    posedge
    0.65
     obstructed
    0.52
     how
    0.50
    ellemző
    0.47
     damaged
    0.47
    rusted
    0.46
     secretory
    0.46
    новништво
    0.45
    ofold
    0.45
    Activations Density 0.014%

    No Known Activations