© 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. 14394
    Prev
    Next
    INDEX
    Explanations

    air

    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
     air
    -0.87
     Air
    -0.83
     airs
    -0.82
     AIR
    -0.77
    airs
    -0.74
     Airs
    -0.72
    AIR
    -0.72
    air
    -0.70
    Air
    -0.68
     Atmospheric
    -0.67
    POSITIVE LOGITS
    tagext
    0.66
    DebuggerNonUser
    0.59
    StoryboardSegue
    0.57
    flow
    0.51
     defaultstate
    0.51
    star
    0.50
     समीक्षक
    0.50
    getSeconds
    0.49
    fill
    0.47
    complexContent
    0.47
    Activations Density 0.011%

    No Known Activations