© 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. 77794
    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
    IsContent
    -0.49
    kins
    -0.44
    arau
    -0.39
    Neu
    -0.36
    gili
    -0.35
    SU
    -0.35
    kimi
    -0.35
    im
    -0.34
     
    -0.34
    kin
    -0.34
    POSITIVE LOGITS
     program
    0.90
    programme
    0.85
    program
    0.83
     programme
    0.81
     press
    0.78
    
    0.77
     Program
    0.77
     PROGRAM
    0.76
    NameInMap
    0.76
     initComponents
    0.76
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.