© 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. 4-CLT-HP
    7. 1007
    Prev
    Next
    INDEX
    Explanations

    als

    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
    GraphicsUnit
    -0.51
     Sélectionnez
    -0.47
    ंदीखरीदारी
    -0.46
     Мексичка
    -0.46
    atguigu
    -0.45
     rhestr
    -0.45
     كومونز
    -0.45
     onResponse
    -0.44
    +#+#
    -0.44
    Sucesor
    -0.43
    POSITIVE LOGITS
    UVWXYZ
    0.61
     سكانية
    0.60
    numerusform
    0.59
    ruptedException
    0.58
    UnsafeEnabled
    0.54
    AutoresizingMask
    0.54
     pitch
    0.52
    FormTagHelper
    0.52
     InputDecoration
    0.52
    koop
    0.52
    Activations Density 0.030%

    No Known Activations