© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43756
    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
    -1.09
     Air
    -1.02
    air
    -1.00
    Air
    -0.88
     AIR
    -0.85
     aire
    -0.84
    AIR
    -0.79
    aire
    -0.75
     Aire
    -0.73
    verwijspagina
    -0.70
    POSITIVE LOGITS
    ing
    1.07
    er
    0.80
    es
    0.71
    ING
    0.71
    ers
    0.69
    s
    0.69
    ingly
    0.65
    starch
    0.63
    ings
    0.61
    orianCalendar
    0.59
    Activations Density 1.486%

    No Known Activations