© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1610
    Prev
    Next
    INDEX
    Explanations

    random strings and abbreviations

    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
    transQ
    -0.47
     are
    -0.46
     reso
    -0.42
     active
    -0.41
     executive
    -0.41
     takes
    -0.41
     Abel
    -0.41
    χαν
    -0.41
     taking
    -0.41
     took
    -0.41
    POSITIVE LOGITS
     disambiguazione
    0.86
    :✨
    0.72
    SharedDtor
    0.69
     kaynağından
    0.68
    Hozzáférés
    0.63
    mybatisplus
    0.63
    Obrázky
    0.61
    pulumi
    0.60
    WireFormatLite
    0.60
     مشين
    0.60
    Activations Density 0.003%

    No Known Activations