© 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. 73105
    Prev
    Next
    INDEX
    Explanations

    motor/motion

    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
     AssemblyCulture
    -0.93
     يتيمه
    -0.91
    ThroughAttribute
    -0.88
    Personendaten
    -0.86
     незавершена
    -0.83
    elemField
    -0.77
    NameInMap
    -0.77
    Portale
    -0.75
     pinulongan
    -0.75
     nahilalakip
    -0.73
    POSITIVE LOGITS
     programming
    0.34
    ABN
    0.33
    COMMAND
    0.32
    minas
    0.32
     getResources
    0.32
     infeksi
    0.32
     programs
    0.32
    리를
    0.32
     program
    0.31
    $__
    0.31
    Activations Density 0.002%

    No Known Activations