© 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. 4-CLT-HP
    7. 2896
    Prev
    Next
    INDEX
    Explanations

    formal writing excerpts

    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
     chuva
    -0.53
     stars
    -0.51
    ثيل
    -0.50
    struct
    -0.46
    obacz
    -0.46
    hits
    -0.46
     didst
    -0.45
    star
    -0.45
    field
    -0.45
     hits
    -0.45
    POSITIVE LOGITS
     AssemblyCulture
    0.68
    ')['
    0.65
    ftagPool
    0.64
    ↵
    0.58
     referenties
    0.56
     ivelany
    0.55
    UpInside
    0.55
    dymyr
    0.53
     EconPapers
    0.53
    UrlResolution
    0.52
    Activations Density 0.000%

    No Known Activations