© 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. 20-CLT-HP
    7. 77646
    Prev
    Next
    INDEX
    Explanations

    White and brown colors

    np_max-act-logits · 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
    Portail
    -0.69
    StructEnd
    -0.64
     enfans
    -0.62
     tiroirs
    -0.62
     AssemblyCompany
    -0.60
     équilibr
    -0.60
     Wreath
    -0.59
     fermés
    -0.59
    simpleType
    -0.58
     gesloten
    -0.58
    POSITIVE LOGITS
     white
    0.85
     brown
    0.82
    brown
    0.71
     Brown
    0.65
    white
    0.63
     White
    0.63
    Brown
    0.61
     browning
    0.58
    White
    0.58
     beige
    0.57
    Activations Density 0.003%

    No Known Activations