© 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. 5-CLT-HP
    7. 5825
    Prev
    Next
    INDEX
    Explanations

    scientific/technical processes

    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
    Билгалдахарш
    -0.79
    SourceChecksum
    -0.75
     EconPapers
    -0.75
    :✨
    -0.65
     Normdatei
    -0.64
     recens
    -0.63
    ContentAsync
    -0.62
    setVerticalGroup
    -0.61
    CDCl
    -0.61
    ništ
    -0.60
    POSITIVE LOGITS
    MigrationBuilder
    0.45
     MRP
    0.44
    */;
    0.43
    drawImage
    0.42
    GTC
    0.42
     TDC
    0.42
     eut
    0.41
    ubb
    0.41
    ])/
    0.41
    줍
    0.41
    Activations Density 0.001%

    No Known Activations