© 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. 20-CLT-HP
    7. 78018
    Prev
    Next
    INDEX
    Explanations

    multi

    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
    Negative Logits
     crescere
    -0.46
    expandindo
    -0.44
     spagno
    -0.43
     duquel
    -0.42
     än
    -0.42
     tão
    -0.40
     Hongrie
    -0.40
    ADELPHIA
    -0.40
     vermelhas
    -0.40
     montañas
    -0.39
    POSITIVE LOGITS
    matchCondition
    0.69
    esModule
    0.68
     Bore
    0.67
     Shade
    0.66
     Locks
    0.65
     Wrap
    0.64
    locks
    0.63
     Hook
    0.61
     Base
    0.61
     poo
    0.59
    Activations Density 0.023%

    No Known Activations