© 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. 91119
    Prev
    Next
    INDEX
    Explanations

    awaiting

    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
     Maat
    -0.52
     always
    -0.50
     oog
    -0.47
     levels
    -0.46
     displaced
    -0.45
     Dulce
    -0.45
     Brethren
    -0.45
    icitis
    -0.45
     downward
    -0.44
     Pliocene
    -0.44
    POSITIVE LOGITS
     stället
    1.02
     normaux
    0.98
     varandra
    0.96
     supérieurs
    0.93
     pertes
    0.91
     feroit
    0.90
     négociations
    0.90
     lèvres
    0.90
     boî
    0.89
     découver
    0.88
    Activations Density 0.000%

    No Known Activations