© 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. 1738
    Prev
    Next
    INDEX
    Explanations

    ARDS

    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
     AssemblyProduct
    -0.62
    textwidth
    -0.58
    ầng
    -0.57
     Cæsar
    -0.55
    tector
    -0.54
    RectangleBorder
    -0.54
     itſelf
    -0.54
     MMC
    -0.52
    دانشنامهٔ
    -0.52
     photolibrary
    -0.50
    POSITIVE LOGITS
     kasarigan
    0.68
    קישורים
    0.59
     препратки
    0.59
    Nuorodos
    0.53
    nip
    0.52
    ிர
    0.52
    nis
    0.50
    ann
    0.50
    项
    0.50
    Portale
    0.49
    Activations Density 0.043%

    No Known Activations