© 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. 0-CLT-HP
    7. 40119
    Prev
    Next
    INDEX
    Explanations

    legal/technical documents

    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
    hib
    -1.70
     bidding
    -0.80
     Bidding
    -0.64
     LST
    -0.62
     RSSSF
    -0.61
    HIB
    -0.57
     pleaſure
    -0.54
    xFFFFFFFF
    -0.54
    hibi
    -0.52
     wherefore
    -0.51
    POSITIVE LOGITS
    httphttps
    0.66
    setVerticalGroup
    0.57
    脚注の使い方
    0.52
    PMailer
    0.51
    новништво
    0.51
    ⊱
    0.51
    OCCURRED
    0.50
    ymce
    0.50
    ensões
    0.49
     发表于
    0.49
    Activations Density 0.027%

    No Known Activations