© 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. 77233
    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
     Вікі
    -0.68
     ویکی‌پدیا
    -0.68
     centres
    -0.67
     sessile
    -0.64
    mpto
    -0.63
     stabilisation
    -0.62
     propOrder
    -0.60
     GenerationType
    -0.60
     Tuli
    -0.60
     calldata
    -0.59
    POSITIVE LOGITS
     Shared
    0.59
     shared
    0.47
     Core
    0.47
     indisponible
    0.43
    Shared
    0.43
    shared
    0.39
     beam
    0.39
    MockBean
    0.38
     Beam
    0.38
    ลิต
    0.37
    Activations Density 0.000%

    No Known Activations