© 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. 77661
    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
    RegressionTest
    -0.84
    abestanden
    -0.71
    tagHelper
    -0.67
     insuffisamment
    -0.64
    lapsingToolbar
    -0.61
    hoea
    -0.60
    oa̍t
    -0.60
    reactstrap
    -0.58
    клопе
    -0.58
     désolés
    -0.57
    POSITIVE LOGITS
     Penit
    0.41
    volles
    0.41
    Bissau
    0.40
     värld
    0.40
     ImGui
    0.39
    zości
    0.38
     pauvreté
    0.36
     réalisation
    0.35
    avad
    0.35
    álat
    0.35
    Activations Density 0.005%

    No Known Activations