© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72905
    Prev
    Next
    INDEX
    Explanations

    primary

    np_max-act-logits · 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
    mybatisplus
    -0.87
    ✭✭
    -0.75
    :✨
    -0.71
    /***/
    -0.59
    脚注の使い方
    -0.59
    ]<<"
    -0.58
    HOLY
    -0.57
    帖最后由
    -0.57
     Bíblia
    -0.57
    Distribuzione
    -0.56
    POSITIVE LOGITS
     ha
    0.67
     pat
    0.63
     Pat
    0.56
     disambiguazione
    0.54
     CreateTagHelper
    0.53
     conci
    0.49
     ujednoznacz
    0.49
     Ambro
    0.48
    Pat
    0.48
     vitae
    0.48
    Activations Density 0.000%

    No Known Activations