© 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. 6248
    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
    Negative Logits
    ]<<"
    -0.54
    windowFixed
    -0.52
     lecturing
    -0.51
     reproach
    -0.49
     surveying
    -0.47
     reser
    -0.45
     corporal
    -0.45
     OMITBAD
    -0.44
     commission
    -0.44
     contextLoads
    -0.44
    POSITIVE LOGITS
    críbete
    0.55
     esternos
    0.53
    ormais
    0.50
    Bạn
    0.50
    Искәрмәләр
    0.50
     ostavi
    0.49
    Παραπομπές
    0.49
    You
    0.49
    kilde
    0.48
    InputTagHelper
    0.47
    Activations Density 0.000%

    No Known Activations