© 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. 77653
    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
     CreateTagHelper
    -1.07
    !*\
    -0.70
    ransition
    -0.69
    Personensuche
    -0.68
     HasFactory
    -0.65
     GeoNames
    -0.64
    ArgsConstructor
    -0.63
    انيف
    -0.62
     Decision
    -0.61
    findpost
    -0.61
    POSITIVE LOGITS
     Horse
    0.38
    Horse
    0.38
    Frog
    0.38
     Coffin
    0.37
    kubectl
    0.37
    horse
    0.36
     LoggerFactory
    0.36
    MethodManager
    0.36
     NHK
    0.36
    ReusableCell
    0.35
    Activations Density 0.003%

    No Known Activations