© 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. 71419
    Prev
    Next
    INDEX
    Explanations

    say the ending -tive/-lat/-tional/-tor/-atory

    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
     CreateTagHelper
    -0.66
    providedIn
    -0.63
    AppMethodBeat
    -0.63
     propOrder
    -0.63
     الحره
    -0.59
    abestanden
    -0.58
    greenrobot
    -0.57
     estekak
    -0.56
     Finley
    -0.56
     eliminated
    -0.54
    POSITIVE LOGITS
     mourut
    0.58
    matory
    0.53
     InputDecoration
    0.52
     DSC
    0.49
     للمعارف
    0.48
     racconto
    0.46
    quy
    0.45
     uVar
    0.45
    veness
    0.44
     Universitaria
    0.43
    Activations Density 0.001%

    No Known Activations