© 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. 5-CLT-HP
    7. 5414
    Prev
    Next
    INDEX
    Explanations

    Austin

    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
    ItemBackground
    -0.58
     kasarigan
    -0.57
     tromper
    -0.55
     biografias
    -0.54
     onCancelled
    -0.54
    sträger
    -0.53
    يكب
    -0.51
    OGND
    -0.50
    reathe
    -0.49
    httphttps
    -0.49
    POSITIVE LOGITS
     NRK
    0.53
    UnsafeEnabled
    0.49
     veneta
    0.48
     Paglinawan
    0.47
    ChildScrollView
    0.47
     Winona
    0.47
    illigen
    0.47
    tract
    0.47
    okovic
    0.46
    bolistas
    0.46
    Activations Density 0.005%

    No Known Activations