© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3557
    Prev
    Next
    INDEX
    Explanations

    also

    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
     незавершена
    -0.45
    IsContent
    -0.44
    httphttps
    -0.43
     dé
    -0.43
     semi
    -0.40
    contentLoaded
    -0.40
     Semi
    -0.39
    лова
    -0.39
    Lưu
    -0.39
    ("")]
    -0.38
    POSITIVE LOGITS
     humanas
    0.69
     umana
    0.66
    seamnă
    0.64
    IUrlHelper
    0.64
    forKey
    0.63
     juridiques
    0.62
     forKey
    0.61
     onAnimation
    0.60
     nationaux
    0.60
     charité
    0.59
    Activations Density 0.005%

    No Known Activations