© 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. 348
    Prev
    Next
    INDEX
    Explanations

    about/on

    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
    better
    -0.51
    Better
    -0.49
     lebih
    -0.41
     tendenza
    -0.41
    more
    -0.40
     még
    -0.40
     moelle
    -0.40
     more
    -0.39
     better
    -0.38
     migliore
    -0.38
    POSITIVE LOGITS
    tagext
    0.92
    TestingModule
    0.90
     GenerationType
    0.82
     AssemblyTitle
    0.81
    setVerticalGroup
    0.79
     StringTokenizer
    0.79
    InstrumentedTest
    0.76
    +:+
    0.75
     this
    0.74
    awtextra
    0.73
    Activations Density 0.016%

    No Known Activations