© 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. 75898
    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
     تضيفلها
    -0.70
     pinulongan
    -0.70
    MemoryWarning
    -0.69
    AutoField
    -0.66
    
    -0.65
    ThroughAttribute
    -0.60
    UnusedPrivate
    -0.58
    contentLoaded
    -0.56
    ércoles
    -0.54
     otomatig
    -0.54
    POSITIVE LOGITS
     sawing
    0.69
     chopping
    0.60
     pumping
    0.56
     punching
    0.54
     figure
    0.54
    Cars
    0.53
     Figs
    0.52
     Pingback
    0.52
     slicing
    0.52
     hooking
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.