© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93382
    Prev
    Next
    INDEX
    Explanations

    questions and requests

    np_max-act · gemini-2.0-flash
    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
    elemField
    -0.73
     iſt
    -0.68
     Wikimedijinoj
    -0.66
     useAppContext
    -0.65
     consumables
    -0.63
     विश्वसनीयता
    -0.63
     kasarigan
    -0.63
    QMetaType
    -0.63
     gynhyrchwyd
    -0.63
    erialize
    -0.62
    POSITIVE LOGITS
     so
    0.45
     and
    0.42
     (
    0.42
     så
    0.41
     &
    0.40
     FetchType
    0.40
     tão
    0.40
    젝
    0.39
     bijna
    0.39
     pře
    0.38
    Activations Density 0.001%

    No Known Activations