© 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. 0-CLT-HP
    7. 1557
    Prev
    Next
    INDEX
    Explanations

    Linnaeus

    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
    lin
    -0.85
    Portail
    -0.63
     ModelExpression
    -0.63
    MigrationBuilder
    -0.63
    ata
    -0.60
    abestanden
    -0.59
    pa
    -0.59
    carrier
    -0.58
    bation
    -0.57
    الحياه
    -0.56
    POSITIVE LOGITS
    erden
    0.55
    prechpartner
    0.55
    ebra
    0.54
    er
    0.54
    erdin
    0.52
    ivably
    0.52
     صوتيه
    0.52
    isasi
    0.51
    nsec
    0.50
    \|^{
    0.50
    Activations Density 0.683%

    No Known Activations