© 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. 20-CLT-HP
    7. 72254
    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
    apimachinery
    -0.57
    intahan
    -0.54
    "}";
    -0.51
    Geografi
    -0.50
    جغرافيا
    -0.50
    SBATCH
    -0.49
    MemoryWarning
    -0.47
      (
    -0.47
    AppCompat
    -0.46
    pegno
    -0.46
    POSITIVE LOGITS
     hard
    0.69
     åt
    0.59
     mergeFrom
    0.58
     go
    0.55
    DebuggerStep
    0.55
    StreamReader
    0.54
     المعيارى
    0.54
    Hard
    0.53
    hard
    0.52
    StreamWriter
    0.51
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.