© 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. 76832
    Prev
    Next
    INDEX
    Explanations

    air

    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
    ganu
    -0.67
    ValueStyle
    -0.66
    Portale
    -0.65
    reportWebVitals
    -0.61
    ownic
    -0.59
     Paglinawan
    -0.59
     valour
    -0.58
    Obrázky
    -0.58
    ждународ
    -0.57
    igshid
    -0.57
    POSITIVE LOGITS
     air
    0.77
    Air
    0.69
    air
    0.66
     Air
    0.65
     lucht
    0.59
    +#+#
    0.57
     AIR
    0.55
     aire
    0.53
    AIR
    0.53
     createState
    0.51
    Activations Density 0.000%

    No Known Activations