© 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. 5-CLT-HP
    7. 3300
    Prev
    Next
    INDEX
    Explanations

    programming code/text

    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
    出版年
    -0.69
    onAttach
    -0.69
    ]")]
    -0.67
    最快更新
    -0.66
     ***!
    -0.64
    jsonwebtoken
    -0.63
    IConfiguration
    -0.62
    phalt
    -0.62
    dafx
    -0.60
     OnInit
    -0.59
    POSITIVE LOGITS
    下载附件
    0.56
     good
    0.52
    SystemColors
    0.50
    enden
    0.50
    lor
    0.47
     visits
    0.47
     Rupert
    0.46
     numbers
    0.45
     guten
    0.45
    不见
    0.45
    Activations Density 0.204%

    No Known Activations