© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3003
    Prev
    Next
    INDEX
    Explanations

    thinking

    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
    RegressionTest
    -0.95
     ModelExpression
    -0.79
    __':
    -0.77
    MigrationBuilder
    -0.77
    Хьажоргаш
    -0.69
    __":
    -0.68
    exitRule
    -0.66
    NameInMap
    -0.64
    verwijspagina
    -0.63
    WithIOException
    -0.63
    POSITIVE LOGITS
     doing
    0.49
    tiga
    0.47
     zeg
    0.46
     getting
    0.45
     discovering
    0.44
     playing
    0.43
    π
    0.43
     π
    0.42
    ére
    0.42
    pering
    0.42
    Activations Density 0.002%

    No Known Activations