© 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. 20-CLT-HP
    7. 71314
    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
    achal
    -0.41
     CreateTagHelper
    -0.37
    Interaction
    -0.36
     MISS
    -0.36
     fined
    -0.36
    igshid
    -0.36
    喧
    -0.36
    Тан
    -0.36
    AsUp
    -0.35
     apar
    -0.35
    POSITIVE LOGITS
    پیوند
    0.71
     useContext
    0.65
    
    0.65
     تكبرها
    0.65
    avoit
    0.62
    tagHelperRunner
    0.60
     виправивши
    0.60
    Personendaten
    0.60
    VolleyError
    0.59
     resourceCulture
    0.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.