© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 2843
    Prev
    Next
    INDEX
    Explanations

    various topics and 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
     racines
    -0.44
    AnimationsModule
    -0.42
     täv
    -0.42
     vänner
    -0.40
    ntä
    -0.40
     irmã
    -0.40
     rayures
    -0.39
     käytet
    -0.39
     quantités
    -0.38
    Спасылкі
    -0.38
    POSITIVE LOGITS
    waitKey
    0.73
     convertView
    0.70
    izations
    0.66
    udges
    0.66
    stdc
    0.65
     Piaget
    0.65
     vulgaires
    0.64
    CopyWith
    0.63
    tagHelperRunner
    0.62
    المناصب
    0.61
    Activations Density 0.003%

    No Known Activations