© 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. 302
    Prev
    Next
    INDEX
    Explanations

    code, database, bathrooms

    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
    oa̍t
    -0.62
     pinulongan
    -0.62
     propOrder
    -0.54
    ProcessEvent
    -0.52
     estekak
    -0.51
    posedge
    -0.48
    führen
    -0.47
    vement
    -0.47
    Personendaten
    -0.46
    SerializedName
    -0.45
    POSITIVE LOGITS
    PhysRevD
    0.53
    culosis
    0.51
    AttributedString
    0.50
     Ril
    0.48
    strado
    0.48
    katalog
    0.47
    Javadoc
    0.47
    enderror
    0.46
     Heilig
    0.46
    قایناق‌لار
    0.46
    Activations Density 0.001%

    No Known Activations