© 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. 517
    Prev
    Next
    INDEX
    Explanations

    regeneration

    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
    Năm
    -0.51
     with
    -0.50
     avec
    -0.48
     通販
    -0.47
    oyer
    -0.47
     препратки
    -0.46
     dengan
    -0.46
    עם
    -0.45
     ExecuteAsync
    -0.44
     With
    -0.43
    POSITIVE LOGITS
    مصادر
    0.77
    ########.
    0.71
    principalTable
    0.70
    WireFormatLite
    0.69
     noqa
    0.68
    يميديا
    0.66
    typeorm
    0.64
    
    0.63
    ToScroll
    0.63
    Jeografia
    0.62
    Activations Density 0.000%

    No Known Activations