© 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. 97048
    Prev
    Next
    INDEX
    Explanations

    .*

    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
    Бахар
    -0.56
     viewType
    -0.56
    (!__
    -0.50
    WebpackPlugin
    -0.45
    ha
    -0.44
    semb
    -0.44
    webElementGuid
    -0.43
    emang
    -0.43
    errer
    -0.43
    cher
    -0.43
    POSITIVE LOGITS
    ſelves
    0.68
     Conſ
    0.66
     Majefty
    0.63
     Reſ
    0.63
     houſe
    0.63
    ſelf
    0.63
     ſmall
    0.62
     faſt
    0.62
     Eſ
    0.61
     Diſ
    0.61
    Activations Density 0.002%

    No Known Activations