© 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. 281
    Prev
    Next
    INDEX
    Explanations

    Spleen/medical research

    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
    exitRule
    -0.62
    RegressionTest
    -0.60
     HttpNotFound
    -0.58
    stu
    -0.56
     argparse
    -0.54
     khán
    -0.52
     DENSITY
    -0.52
     raso
    -0.52
     Partagez
    -0.52
    rungsseite
    -0.51
    POSITIVE LOGITS
    примеча
    0.58
    دانشنامهٔ
    0.49
     Soma
    0.44
    openConnection
    0.44
    Ety
    0.41
    MethodManager
    0.40
    cooling
    0.40
    ArrowToggle
    0.40
    MigrationBuilder
    0.40
    extAlignment
    0.39
    Activations Density 0.001%

    No Known Activations