© 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. 5-CLT-HP
    4. 96835
    Prev
    Next
    INDEX
    Explanations

    from

    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
    ///</
    -0.66
     disambiguazione
    -0.59
     "..\..\..\
    -0.59
    >>();
    -0.56
     "..\..\
    -0.56
    argc
    -0.54
    GEBURTSDATUM
    -0.51
    crose
    -0.51
    >>()
    -0.50
    principalTable
    -0.50
    POSITIVE LOGITS
    AnimationsModule
    0.69
     للمعارف
    0.69
    RectangleBorder
    0.65
     this
    0.65
    Obrázky
    0.55
     ویکی‌پدی
    0.55
    __(/*!
    0.55
    VersionUID
    0.54
    WriteAttribute
    0.54
     genoux
    0.54
    Activations Density 0.001%

    No Known Activations