© 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. 98105
    Prev
    Next
    INDEX
    Explanations

    accidents

    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
    coda
    -0.46
     ra
    -0.43
     v
    -0.43
    ILON
    -0.40
    ?.
    -0.39
    lès
    -0.39
    печат
    -0.39
     tr
    -0.39
     op
    -0.38
    ek
    -0.38
    POSITIVE LOGITS
    AccessorTable
    0.84
    ConstraintMaker
    0.84
    ContentAsync
    0.80
    IsContent
    0.77
    GOTREF
    0.72
    #+#
    0.70
     سكانية
    0.70
     Roskov
    0.70
     архивлан
    0.69
     AssemblyProduct
    0.68
    Activations Density 0.002%

    No Known Activations