© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95092
    Prev
    Next
    INDEX
    Explanations

    Wes

    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
    ilion
    -0.94
    findpost
    -0.83
    Personendaten
    -0.71
    richTextPanel
    -0.69
     AssemblyCulture
    -0.64
     ujednoznacz
    -0.63
    IDENT
    -0.61
     فريبيس
    -0.61
    libft
    -0.60
    ident
    -0.59
    POSITIVE LOGITS
    HostException
    0.60
     SOCK
    0.56
    \{\\
    0.51
     JpaRepository
    0.48
    en
    0.47
    enab
    0.47
     مشارکت‌کنندگان
    0.47
    URLException
    0.47
     gæ
    0.47
    edan
    0.47
    Activations Density 0.053%

    No Known Activations