© 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. 4-CLT-HP
    7. 1070
    Prev
    Next
    INDEX
    Explanations

    of

    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
    sizeCache
    -0.88
    ստ
    -0.70
    Obrázky
    -0.69
    autoreleasepool
    -0.69
    FormTagHelper
    -0.68
    ModelSerializer
    -0.67
     Савезне
    -0.66
     Dominus
    -0.66
    таратура
    -0.66
    ]),
    -0.65
    POSITIVE LOGITS
    AddTagHelper
    0.35
    wiegend
    0.34
    daction
    0.33
     <<<<<<<<<<<<<<
    0.32
    出版年
    0.32
     chi̍t
    0.32
    ‌ترین
    0.31
    Então
    0.30
    arquivo
    0.29
     padx
    0.29
    Activations Density 0.003%

    No Known Activations