© 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. 14421
    Prev
    Next
    INDEX
    Explanations

    science and academia

    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
     nakalista
    -0.97
     betweenstory
    -0.93
    曖昧さ回避
    -0.86
     CreateTagHelper
    -0.85
     disambiguazione
    -0.84
    Diwedd
    -0.79
    دانشنامهٔ
    -0.76
    帖最后由
    -0.75
     архивлан
    -0.75
    PerformLayout
    -0.74
    POSITIVE LOGITS
     challenging
    0.44
     keterangan
    0.44
     Challenging
    0.43
    chom
    0.43
     déclen
    0.40
     något
    0.39
     lenker
    0.39
     by
    0.38
    ämään
    0.38
     expédi
    0.37
    Activations Density 0.012%

    No Known Activations