© 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. 1-CLT-HP
    7. 16214
    Prev
    Next
    INDEX
    Explanations

    land area

    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
    Negative Logits
    PerformLayout
    -0.85
     hectare
    -0.84
    hecta
    -0.78
     Efq
    -0.73
     portables
    -0.66
    eners
    -0.63
    URLException
    -0.63
    sterious
    -0.63
    expandindo
    -0.63
     mapStateToProps
    -0.62
    POSITIVE LOGITS
    anel
    0.49
     transfieras
    0.48
    IsContent
    0.47
    뀜
    0.47
    ria
    0.42
     infected
    0.42
     indisponible
    0.41
    пі
    0.39
     glass
    0.39
     niñas
    0.39
    Activations Density 0.008%

    No Known Activations