© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 551
    Prev
    Next
    INDEX
    Explanations

    code/technical texts

    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
    AndEndTag
    -0.74
     AssemblyTitle
    -0.71
    ########.
    -0.68
    wußt
    -0.66
     يتيمه
    -0.62
    dientemente
    -0.61
    chemy
    -0.61
     JAXBElement
    -0.59
     Cataloging
    -0.57
    annica
    -0.57
    POSITIVE LOGITS
    sat
    0.46
    Искәрмәләр
    0.45
    MessageOf
    0.44
     stream
    0.44
     present
    0.43
     profil
    0.42
     program
    0.42
    met
    0.42
    ublik
    0.42
    вни
    0.41
    Activations Density 0.013%

    No Known Activations