© 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. 15630
    Prev
    Next
    INDEX
    Explanations

    r

    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
    <bos>
    -0.74
    netinet
    -0.45
    Cyfeiriadau
    -0.44
    Germain
    -0.44
     supervivencia
    -0.44
     Мексичка
    -0.43
    hm
    -0.42
     meisten
    -0.42
     meeste
    -0.41
    PER
    -0.39
    POSITIVE LOGITS
     CreateTagHelper
    0.81
    parsedMessage
    0.75
    AnchorStyles
    0.71
    Géographie
    0.65
    Kariera
    0.64
    contentLoaded
    0.63
    postIndex
    0.63
     eventName
    0.63
    richTextPanel
    0.63
    KURZBESCHREIBUNG
    0.62
    Activations Density 0.038%

    No Known Activations