© 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. 20-CLT-HP
    7. 75448
    Prev
    Next
    INDEX
    Explanations

    purity

    np_max-act-logits · 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
    MigrationBuilder
    -0.87
     الرياضيه
    -0.69
    NameInMap
    -0.66
     EconPapers
    -0.61
    thâu
    -0.61
    CppMethod
    -0.60
     دیکھیے
    -0.60
    évaluateur
    -0.58
    WithIOException
    -0.57
    KommentareTeilen
    -0.56
    POSITIVE LOGITS
     pure
    0.54
    essence
    0.50
    pure
    0.50
     essence
    0.49
     pur
    0.49
     concentrate
    0.49
    Pure
    0.48
     powder
    0.47
     pieces
    0.47
    ]--;
    0.47
    Activations Density 0.000%

    No Known Activations