© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43781
    Prev
    Next
    INDEX
    Explanations

    sub

    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
     sub
    -1.33
     pre
    -1.14
     Sub
    -1.01
     Pre
    -0.86
    ,
    -0.73
    Sub
    -0.72
     in
    -0.70
     
    -0.67
     res
    -0.66
     (
    -0.66
    POSITIVE LOGITS
     feroit
    1.02
     enfans
    0.98
     énergé
    0.96
     imprimée
    0.95
     pauvres
    0.95
     anún
    0.94
     mauvaises
    0.93
     auroit
    0.93
     automatiques
    0.92
     varandra
    0.91
    Activations Density 0.115%

    No Known Activations