© 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. 938
    Prev
    Next
    INDEX
    Explanations

    Working with data

    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
    mybatisplus
    -0.56
    AndEndTag
    -0.56
     davon
    -0.52
    uresti
    -0.51
     bale
    -0.49
    GeneratedValue
    -0.48
     Neumann
    -0.48
     setCode
    -0.48
     Hệ
    -0.48
     Boyer
    -0.47
    POSITIVE LOGITS
     per
    0.60
     daily
    0.53
    !***
    0.51
    afficheront
    0.50
     everyday
    0.50
    IContainer
    0.47
    toHaveBeenCalled
    0.47
    ariki
    0.47
     vsak
    0.47
    spyOn
    0.47
    Activations Density 0.002%

    No Known Activations