© 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. 5-CLT-HP
    7. 92245
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     arşivlendi
    -0.75
    ########.
    -0.73
    +#+#
    -0.63
    فایل‌لار
    -0.62
    клопе
    -0.61
    Personendaten
    -0.61
    ագրություններ
    -0.60
    WithIOException
    -0.59
     Вікі
    -0.59
    awtextra
    -0.59
    POSITIVE LOGITS
     فريبيس
    0.57
     thoſe
    0.57
     Passer
    0.56
     StringIO
    0.56
     alſo
    0.56
     ſhall
    0.56
     juſt
    0.54
     Tind
    0.53
     kennt
    0.52
    huur
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.