© 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. 1-CLT-HP
    7. 9458
    Prev
    Next
    INDEX
    Explanations

    ary

    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
     autorytatywna
    -0.72
     AssemblyTitle
    -0.69
     betweenstory
    -0.68
    Datuak
    -0.62
    تقاوى
    -0.60
     protoimpl
    -0.59
    AndEndTag
    -0.59
    #+#
    -0.58
     CreateTagHelper
    -0.57
    Chham
    -0.55
    POSITIVE LOGITS
    BagLayout
    0.59
    GBT
    0.52
    zzleHttp
    0.48
    ameter
    0.47
    fist
    0.46
     individuale
    0.46
    DataColumn
    0.46
    hopper
    0.44
    ski
    0.44
    worm
    0.44
    Activations Density 0.024%

    No Known Activations