© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76123
    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
     InputDecoration
    -0.55
    FormTagHelper
    -0.51
    Descriere
    -0.48
     Administrativna
    -0.46
    insee
    -0.44
    Šaltiniai
    -0.43
    }{||
    -0.43
    Carreira
    -0.43
    arschu
    -0.42
    kuuta
    -0.42
    POSITIVE LOGITS
     '{@
    0.73
    Билгалдахарш
    0.66
     autorytatywna
    0.63
     Mudd
    0.58
    存于互联网档案馆
    0.58
    ChildScrollView
    0.56
     HasFactory
    0.55
    . 
    0.54
    ختی
    0.54
    tikzpicture
    0.53
    Activations Density 0.008%

    No Known Activations