© 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. 1-CLT-HP
    7. 15584
    Prev
    Next
    INDEX
    Explanations

    machinery

    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
     machine
    -0.94
     machinery
    -0.91
    machine
    -0.82
     MACHINE
    -0.82
     Machinery
    -0.82
     Machine
    -0.82
    MACHINE
    -0.81
     machines
    -0.76
    Machine
    -0.75
     Machines
    -0.75
    POSITIVE LOGITS
    names
    0.52
    downarrow
    0.52
     насељу
    0.51
     Gibbon
    0.48
    Transkript
    0.47
    arraycopy
    0.46
     pinulongan
    0.45
    soort
    0.44
    lineTo
    0.44
    Unmount
    0.44
    Activations Density 0.016%

    No Known Activations