© 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. 3580
    Prev
    Next
    INDEX
    Explanations

    and

    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
    Such
    -0.68
     Such
    -0.65
     niego
    -0.61
    such
    -0.57
     такую
    -0.56
     solcher
    -0.55
     has
    -0.54
    <bos>
    -0.52
     Particularly
    -0.52
     dalamnya
    -0.51
    POSITIVE LOGITS
     CreateTagHelper
    0.87
     they
    0.86
     مشين
    0.76
    RenderAtEndOf
    0.75
     each
    0.67
    Παραπομπές
    0.66
    richTextPanel
    0.65
     AssemblyTitle
    0.63
     виправивши
    0.62
    +#+#
    0.60
    Activations Density 0.002%

    No Known Activations