© 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. 4-CLT-HP
    7. 1110
    Prev
    Next
    INDEX
    Explanations

    children

    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
     дописавши
    -0.80
    HasIndex
    -0.69
     BrowserModule
    -0.65
     تضيفلها
    -0.64
     ProtoMessage
    -0.63
    ValueStyle
    -0.63
    serves
    -0.62
    ViewImports
    -0.59
     jScrollPane
    -0.58
     aprilie
    -0.57
    POSITIVE LOGITS
     with
    0.59
    MENAFN
    0.52
     transfer
    0.50
    tamol
    0.48
    ❋
    0.48
     label
    0.47
     learn
    0.47
     kenal
    0.47
     As
    0.47
     stay
    0.46
    Activations Density 0.002%

    No Known Activations