© 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. 20-CLT-HP
    7. 77863
    Prev
    Next
    INDEX
    Explanations

    Formal, technical content

    np_max-act-logits · 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
     FormBuilder
    -0.53
     يتيمه
    -0.50
    fjspx
    -0.48
    RenderAtEndOf
    -0.48
     Excerpt
    -0.47
     MessageBoxIcon
    -0.47
    ρων
    -0.45
    SX
    -0.44
    __["
    -0.44
    enderror
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.57
    معلومات
    0.55
    IsContent
    0.55
    photobucket
    0.55
    StructEnd
    0.54
    Hentet
    0.54
     محفوظة
    0.51
     pitié
    0.50
     HttpNotFound
    0.50
    ाहरण
    0.49
    Activations Density 0.003%

    No Known Activations