© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 441
    Prev
    Next
    INDEX
    Explanations

    large

    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
    LookAnd
    -0.88
    期刊论文
    -0.75
    LayoutStyle
    -0.71
    ArgsConstructor
    -0.70
    انيف
    -0.66
     ostavi
    -0.63
    lafen
    -0.62
     EconPapers
    -0.60
    Personendaten
    -0.60
    ">:
    -0.59
    POSITIVE LOGITS
     way
    0.82
     WAY
    0.60
    Way
    0.60
     numbers
    0.58
     ways
    0.58
    way
    0.56
     Way
    0.56
    numbers
    0.55
    WAY
    0.52
     measure
    0.48
    Activations Density 0.001%

    No Known Activations