© 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. 0-CLT-HP
    7. 45465
    Prev
    Next
    INDEX
    Explanations

    More

    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
    ing
    -0.52
     cade
    -0.49
     noy
    -0.47
    -
    -0.46
     model
    -0.45
    laka
    -0.44
    (
    -0.44
     جائ
    -0.44
    hadas
    -0.43
     (
    -0.43
    POSITIVE LOGITS
    GEBURTSDATUM
    1.05
    ьаж
    0.98
     disambiguazione
    0.96
    
    0.94
    脚注の使い方
    0.90
     BoxFit
    0.89
    UnsafeEnabled
    0.89
     InputDecoration
    0.88
     utafitiHapana
    0.83
    CppCodeGen
    0.81
    Activations Density 0.052%

    No Known Activations