© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3681
    Prev
    Next
    INDEX
    Explanations

    diapers

    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
     surla
    -0.89
    XmlAccessType
    -0.84
    parsedMessage
    -0.81
    WebVitals
    -0.80
    Autoritní
    -0.78
     OFDb
    -0.76
     <>",
    -0.76
     Theſe
    -0.74
    richTextPanel
    -0.74
    verwijspagina
    -0.71
    POSITIVE LOGITS
     to
    1.22
    to
    0.76
     To
    0.65
    To
    0.58
    到
    0.46
     TO
    0.43
    ToUse
    0.43
    Décès
    0.42
     do
    0.41
     put
    0.41
    Activations Density 0.013%

    No Known Activations