© 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. 0-CLT-HP
    4. 1333
    Prev
    Next
    INDEX
    Explanations

    trough

    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
    id
    -0.90
    idl
    -0.59
    ically
    -0.57
    ires
    -0.56
    ical
    -0.51
     id
    -0.50
    iers
    -0.50
    ilite
    -0.48
    jat
    -0.48
    maketitle
    -0.48
    POSITIVE LOGITS
     beginnetje
    0.89
    IsMutable
    0.73
    ConstraintMaker
    0.72
     pinulongan
    0.70
     kasarigan
    0.68
    StructEnd
    0.66
     وتسجيلات
    0.66
     Paglinawan
    0.65
     ویکی‌پدی
    0.64
     Roskov
    0.64
    Activations Density 0.339%

    No Known Activations