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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2633
    Prev
    Next
    INDEX
    Explanations

    scientific 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
    RenderAtEndOf
    -0.61
    SharedCtor
    -0.57
    ⓧ
    -0.57
     AssemblyCulture
    -0.51
    ंदीखरीदारी
    -0.51
    UINTN
    -0.49
    ésia
    -0.49
    はじめに
    -0.48
     [],
    -0.48
    Péri
    -0.47
    POSITIVE LOGITS
     auguri
    0.54
    mybatisplus
    0.53
    inib
    0.52
     layers
    0.51
     getRule
    0.49
     Völker
    0.49
     plastic
    0.48
    __*/
    0.47
    AndEndTag
    0.47
     polegadas
    0.47
    Activations Density 0.004%

    No Known Activations