© 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. 0-CLT-HP
    7. 41441
    Prev
    Next
    INDEX
    Explanations

    curative

    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
    AntiForgeryToken
    -0.75
    orption
    -0.73
     resolved
    -0.65
     "..\..\
    -0.64
    Datuak
    -0.57
    atari
    -0.53
    BASEPATH
    -0.53
     "..\..\..\
    -0.52
     Save
    -0.52
    InjectAttribute
    -0.50
    POSITIVE LOGITS
     Cæsar
    0.58
    Personensuche
    0.57
    HasAnnotation
    0.56
    ніципалі
    0.54
     merci
    0.54
    تقاوى
    0.52
    DebuggerNonUser
    0.51
    crypt
    0.50
    Bạn
    0.50
    webElementXpaths
    0.50
    Activations Density 1.369%

    No Known Activations