© 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. 8915
    Prev
    Next
    INDEX
    Explanations

    age

    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
    Not in Any Lists

    No Comments

    Negative Logits
    matchCondition
    -0.56
    AnchorStyles
    -0.52
     f
    -0.52
    
    -0.49
     e
    -0.48
     multiple
    -0.47
     val
    -0.47
     שוליים
    -0.47
     excess
    -0.45
    saraba
    -0.45
    POSITIVE LOGITS
     EconPapers
    0.85
     morire
    0.71
     poussière
    0.70
     dedans
    0.69
     répondu
    0.66
     pleaſure
    0.66
     polvere
    0.65
     femininas
    0.64
     Monfieur
    0.62
    AddTagHelper
    0.62
    Activations Density 0.005%

    No Known Activations