© 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. 96486
    Prev
    Next
    INDEX
    Explanations

    Start of document/text

    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
    addContainerGap
    -0.64
    NameInMap
    -0.61
    ProgressHUD
    -0.60
    UnusedPrivate
    -0.60
    Geplaatst
    -0.57
     '+':
    -0.56
    Tracce
    -0.56
     Utilizamos
    -0.55
    AndEndTag
    -0.55
    UrlResolution
    -0.54
    POSITIVE LOGITS
    bitat
    0.48
     trekken
    0.48
    /**
    0.45
    ledo
    0.45
    MessageInfo
    0.43
    kannt
    0.43
     schi
    0.43
     A
    0.43
    edip
    0.43
    +#+#
    0.43
    Activations Density 0.000%

    No Known Activations