© 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. 1553
    Prev
    Next
    INDEX
    Explanations

    expression

    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
     mại
    -0.48
    pread
    -0.48
     surla
    -0.47
    phytes
    -0.45
    rénées
    -0.45
     Пусть
    -0.45
    かしい
    -0.45
     calendriers
    -0.44
    ograms
    -0.44
    tahui
    -0.44
    POSITIVE LOGITS
     Италијани
    0.91
    <bos>
    0.90
    MLLoader
    0.66
    thâu
    0.66
     Italijani
    0.65
     wanting
    0.62
     Ambas
    0.61
     мәкал
    0.60
    lccn
    0.59
     needing
    0.58
    Activations Density 0.011%

    No Known Activations