© 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. 76454
    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
    AndEndTag
    -0.59
     betweenstory
    -0.57
    ENIX
    -0.56
    saraba
    -0.52
    PageModule
    -0.52
    Portály
    -0.47
    DESCRIPTOR
    -0.46
    chin
    -0.46
     &___
    -0.46
    ,‎
    -0.44
    POSITIVE LOGITS
     الحره
    0.79
    
    0.62
     المعيارى
    0.62
     mala
    0.58
    lapses
    0.56
    Quieres
    0.56
    omalies
    0.55
     Numerade
    0.55
    sstil
    0.55
    omaly
    0.54
    Activations Density 0.000%

    No Known Activations