© 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. 20-CLT-HP
    7. 71890
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     nahilalakip
    -0.81
    ruptedException
    -0.77
    MemoryWarning
    -0.71
     Савезне
    -0.71
     مشين
    -0.71
    Билгалдахарш
    -0.64
    Vidite
    -0.64
    latego
    -0.64
    yntaxException
    -0.63
    OGND
    -0.62
    POSITIVE LOGITS
     to
    0.58
    sight
    0.40
    kole
    0.39
     sight
    0.38
     Sight
    0.38
    шо
    0.37
     mum
    0.36
    andon
    0.36
     silent
    0.35
    IES
    0.35
    Activations Density 0.001%

    No Known Activations