© 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. 4-CLT-HP
    7. 4604
    Prev
    Next
    INDEX
    Explanations

    text fragments/colons/parens

    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>
    -0.64
     GenerationType
    -0.59
    ünst
    -0.55
    fetchone
    -0.52
    epik
    -0.52
     EconPapers
    -0.51
    oneof
    -0.50
    انيف
    -0.50
    AccessFile
    -0.49
    awtextra
    -0.48
    POSITIVE LOGITS
     with
    0.72
    исленность
    0.62
     kasarigan
    0.56
    avía
    0.54
    OrWhiteSpace
    0.54
    visionnement
    0.52
    AppMethodBeat
    0.51
    localObject
    0.51
     Wedge
    0.51
     Pneum
    0.50
    Activations Density 0.003%

    No Known Activations