© 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. 5-CLT-HP
    7. 91051
    Prev
    Next
    INDEX
    Explanations

    HTML and web pages

    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
    Personensuche
    -0.82
     OnInit
    -0.54
    OGND
    -0.53
     snippetHide
    -0.52
     kiệm
    -0.49
     peoples
    -0.49
    μού
    -0.49
     clays
    -0.48
     llamas
    -0.48
     dens
    -0.48
    POSITIVE LOGITS
    //
    0.68
     ddelweddau
    0.58
    sidemargin
    0.57
     journaux
    0.56
     anledning
    0.52
     spectateurs
    0.52
     énergé
    0.51
     comigo
    0.51
     prochaines
    0.51
     médicaments
    0.50
    Activations Density 0.000%

    No Known Activations