© 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. 72102
    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
     storici
    -0.76
    berdayakan
    -0.75
     nôtre
    -0.70
     storica
    -0.70
     négociations
    -0.66
     stället
    -0.66
     blessés
    -0.66
     azione
    -0.66
     bershka
    -0.65
     étrangères
    -0.65
    POSITIVE LOGITS
     on
    0.99
     On
    0.63
    CopyWith
    0.58
     ON
    0.57
    On
    0.54
    OGND
    0.51
     <<<<<<<<<<<<<<
    0.51
    Зноскі
    0.49
     на
    0.49
    on
    0.48
    Activations Density 0.009%

    No Known Activations