© 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. 2112
    Prev
    Next
    INDEX
    Explanations

    the

    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
     defaultstate
    -0.70
    IsContent
    -0.61
    newswire
    -0.60
    ThroughAttribute
    -0.60
     kasarigan
    -0.60
    مراجع
    -0.60
    NameInMap
    -0.58
    σθ
    -0.57
    WebElementEntity
    -0.56
     ویکی‌پدی
    -0.56
    POSITIVE LOGITS
    setopt
    0.51
     gemeint
    0.47
    <bos>
    0.47
    attoos
    0.46
    addProduct
    0.43
    odeon
    0.42
    اتو
    0.42
    AddHtmlAttribute
    0.41
    uzzy
    0.41
     undefined
    0.41
    Activations Density 0.011%

    No Known Activations