© 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. 95545
    Prev
    Next
    INDEX
    Explanations

    remember

    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
     remember
    -1.85
    remember
    -1.60
     remembering
    -1.56
     Remember
    -1.55
     remembers
    -1.53
    Remember
    -1.52
     remembered
    -1.45
     REMEMBER
    -1.43
     recall
    -1.40
     Recall
    -1.22
    POSITIVE LOGITS
    Personensuche
    0.83
     typelib
    0.70
     autorytatywna
    0.70
     BoxFit
    0.66
    RegistryLite
    0.63
    Bibliograf
    0.63
    FULLY
    0.60
     مشين
    0.59
     jScrollPane
    0.59
    fully
    0.59
    Activations Density 0.061%

    No Known Activations