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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42723
    Prev
    Next
    INDEX
    Explanations

    observations

    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
     learned
    -0.93
    learned
    -0.90
     learnt
    -0.77
     Learned
    -0.77
     observations
    -0.74
     experiments
    -0.71
     provision
    -0.67
     AI
    -0.63
     спе
    -0.59
     ‘
    -0.59
    POSITIVE LOGITS
     Houſe
    1.16
     houſe
    1.09
     Monfieur
    1.02
     Diſ
    0.97
     Anſ
    0.96
     Jefus
    0.94
     himſelf
    0.93
     ſmall
    0.93
     Reſ
    0.90
     itſelf
    0.90
    Activations Density 2.142%

    No Known Activations