© 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. 672
    Prev
    Next
    INDEX
    Explanations

    descriptions and connecting words

    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
     LEYENDO
    -0.45
    bergement
    -0.42
    hermoso
    -0.40
    zaine
    -0.40
     jih
    -0.40
     recently
    -0.39
    ]--;
    -0.38
    iroz
    -0.38
     own
    -0.38
    SPONSORED
    -0.37
    POSITIVE LOGITS
     NSCoder
    0.77
     ligiloj
    0.74
     numberOfRows
    0.73
     Himo
    0.68
    tagHelperRunner
    0.66
    esModule
    0.66
    下载附件
    0.64
    ValueStyle
    0.64
    omiast
    0.64
    mybatisplus
    0.63
    Activations Density 0.017%

    No Known Activations