© 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. 1-CLT-HP
    7. 9143
    Prev
    Next
    INDEX
    Explanations

    assume

    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
    Obrázky
    -0.73
     resourceCulture
    -0.71
    تقاوى
    -0.66
    expandindo
    -0.64
    脚注の使い方
    -0.63
    BeginContext
    -0.57
     estimés
    -0.51
    出版年
    -0.51
    tagext
    -0.49
    Parcelize
    -0.48
    POSITIVE LOGITS
    itatem
    0.62
    lossenen
    0.54
     Vorg
    0.54
    itanya
    0.53
    saraba
    0.53
    pbs
    0.52
    ITERIA
    0.52
    coni
    0.52
    dani
    0.51
    μφωνα
    0.51
    Activations Density 0.008%

    No Known Activations