© 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. 4737
    Prev
    Next
    INDEX
    Explanations

    Names, entities

    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
     Willy
    -0.56
    finch
    -0.54
     APE
    -0.53
    gv
    -0.49
    offsetWidth
    -0.49
    Willy
    -0.49
    はず
    -0.49
    ритори
    -0.49
    spaceBetween
    -0.49
    ece
    -0.47
    POSITIVE LOGITS
    Portale
    0.69
    getSystemService
    0.65
    pushFollow
    0.63
    jsdelivr
    0.60
    UIColor
    0.56
    DataSnapshot
    0.56
    runApp
    0.53
    tymologie
    0.52
    hotra
    0.52
     MaterialApp
    0.52
    Activations Density 0.003%

    No Known Activations