© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15887
    Prev
    Next
    INDEX
    Explanations

    3 and 4

    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
    mybatisplus
    -0.75
    umb
    -0.63
    ibatis
    -0.51
    الحياه
    -0.50
    bell
    -0.50
    lung
    -0.49
     McCa
    -0.49
    ling
    -0.48
     raised
    -0.47
    اتل
    -0.47
    POSITIVE LOGITS
     Innocence
    0.60
     innocence
    0.59
    rachtet
    0.58
    ResponseWriter
    0.57
    SpringRunner
    0.56
    Tikang
    0.54
     pitches
    0.54
     <<<<<<<<<<<<<<
    0.53
     Rajah
    0.52
     vastaan
    0.52
    Activations Density 0.113%

    No Known Activations