© 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. 1-CLT-HP
    7. 13840
    Prev
    Next
    INDEX
    Explanations

    that

    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
     ExecuteAsync
    -0.65
    MigrationBuilder
    -0.64
     façon
    -0.51
     крайней
    -0.44
     davon
    -0.44
     ciento
    -0.42
     måte
    -0.42
     poveznice
    -0.42
    ريقة
    -0.41
     számára
    -0.40
    POSITIVE LOGITS
     are
    0.76
     monasteries
    0.68
     Majefty
    0.67
     LoggerFactory
    0.65
     superstition
    0.65
     arent
    0.64
     ModelExpression
    0.63
     createSprite
    0.62
     simplify
    0.62
    hésite
    0.62
    Activations Density 0.079%

    No Known Activations