© 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. 5-CLT-HP
    7. 98185
    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
     useRouter
    -0.50
    sidenav
    -0.49
    orElse
    -0.49
     viewType
    -0.46
    wpi
    -0.45
    зулта
    -0.45
     recyclerView
    -0.45
     wikipagina
    -0.45
    GUILayout
    -0.45
    loginPage
    -0.45
    POSITIVE LOGITS
     on
    0.67
    Curse
    0.65
     curse
    0.63
    parsedMessage
    0.61
    PerformLayout
    0.60
    SpringBootTest
    0.57
    curse
    0.57
     Curse
    0.56
    ftagPool
    0.56
    apunov
    0.56
    Activations Density 0.000%

    No Known Activations