© 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. 5-CLT-HP
    7. 91306
    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
    EnableWeb
    -0.43
     vol
    -0.43
    lateinit
    -0.40
    容
    -0.40
     operation
    -0.39
     streets
    -0.39
    gameserver
    -0.38
    invokeLater
    -0.37
     operar
    -0.37
    lp
    -0.37
    POSITIVE LOGITS
    AndEndTag
    0.82
    AccessorTable
    0.71
    __':
    0.66
    __":
    0.64
    FormTagHelper
    0.63
     autorytatywna
    0.62
     propOrder
    0.62
    ostante
    0.61
    Дереккөздер
    0.61
     Савезне
    0.60
    Activations Density 0.003%

    No Known Activations