© 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. 0-CLT-HP
    7. 95348
    Prev
    Next
    INDEX
    Explanations

    ke

    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
    ke
    -1.94
    KE
    -1.47
     ke
    -1.45
    Ke
    -1.36
     Ke
    -1.29
     KE
    -0.96
    ness
    -0.94
    cke
    -0.82
    nya
    -0.81
    keti
    -0.73
    POSITIVE LOGITS
    GraphicsUnit
    0.87
    InjectAttribute
    0.86
    IsContent
    0.83
     незавершена
    0.82
    elemField
    0.79
    IndentedString
    0.70
    ValueStyle
    0.68
    SequentialGroup
    0.67
    windowFixed
    0.65
    LEncoder
    0.63
    Activations Density 1.204%

    No Known Activations