© 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. 5-CLT-HP
    7. 5995
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    SourceChecksum
    -0.84
     跳转至
    -0.55
    fjspx
    -0.54
    createServer
    -0.53
    DISK
    -0.50
     Advanced
    -0.48
    istoitu
    -0.48
    تقاوى
    -0.48
     sẻ
    -0.48
    tagHelperRunner
    -0.48
    POSITIVE LOGITS
    iecie
    0.55
    ruptcy
    0.49
    InitVars
    0.49
     Dernière
    0.48
     Pase
    0.47
    ::::::::::::::::
    0.47
     insuper
    0.47
     OFDb
    0.46
    lossians
    0.45
     Меня
    0.45
    Activations Density 0.001%

    No Known Activations