© 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. 5-CLT-HP
    7. 96916
    Prev
    Next
    INDEX
    Explanations

    among in

    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
     Audiodateien
    -0.79
     parlant
    -0.61
    Various
    -0.56
     mukana
    -0.54
     montrant
    -0.51
     setType
    -0.51
     Various
    -0.51
    Either
    -0.51
    looking
    -0.50
    тки
    -0.49
    POSITIVE LOGITS
    errHandler
    0.65
    SharedDtor
    0.54
     المعيارى
    0.54
    UCN
    0.54
    CppCodeGen
    0.52
     doInBackground
    0.52
    Спољашње
    0.52
     AssemblyProduct
    0.49
     other
    0.48
    AsUp
    0.48
    Activations Density 0.002%

    No Known Activations