© 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. 5-CLT-HP
    7. 96605
    Prev
    Next
    INDEX
    Explanations

    Code and technical documents

    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
    oredCriteria
    -0.87
    +#+#
    -0.60
     Савезне
    -0.59
    تقاوى
    -0.57
    Espèce
    -0.57
     Exacts
    -0.55
    ModelSerializer
    -0.54
     continúas
    -0.54
    ündig
    -0.53
    MigrationBuilder
    -0.52
    POSITIVE LOGITS
     serious
    0.59
     injury
    0.56
     catching
    0.52
     rollover
    0.51
    BeforeMethod
    0.51
    __(/*!
    0.50
    ########.
    0.50
     collision
    0.50
     explosion
    0.50
    Rüyada
    0.49
    Activations Density 0.002%

    No Known Activations