© 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. 5-CLT-HP
    7. 97982
    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
     LoginComponent
    -0.41
    ContentLoaded
    -0.41
     høre
    -0.40
     saja
    -0.40
    исленность
    -0.37
    BagConstraints
    -0.36
     kjø
    -0.36
    kości
    -0.36
    ТС
    -0.36
     mudah
    -0.36
    POSITIVE LOGITS
    хьтан
    0.97
     سكانية
    0.82
     pleaſure
    0.82
     ***!
    0.80
     Administrativna
    0.79
     autorytatywna
    0.78
    tagHelperRunner
    0.78
     AssemblyTitle
    0.77
     uſe
    0.75
     ſp
    0.74
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.