© 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. 3208
    Prev
    Next
    INDEX
    Explanations

    Errors, diagnoses, and chemical processes

    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
    Arbitrage
    -0.56
    Спасылкі
    -0.54
    StructEnd
    -0.51
     blue
    -0.49
    ADORA
    -0.49
     betweenstory
    -0.48
     externa
    -0.47
     InputDecoration
    -0.46
    tabak
    -0.46
    Verse
    -0.46
    POSITIVE LOGITS
    +:+
    0.60
    SpringRunner
    0.60
     Orrell
    0.57
    stateParams
    0.56
    GEBURTS
    0.56
    usermodel
    0.54
     mukaan
    0.54
    LoggerFactory
    0.53
    ConstraintMaker
    0.52
    ContentAsync
    0.52
    Activations Density 0.003%

    No Known Activations