© 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. 95012
    Prev
    Next
    INDEX
    Explanations

    June

    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
     June
    -1.58
     April
    -1.52
     May
    -1.45
     March
    -1.31
     August
    -1.07
     July
    -1.05
     February
    -1.04
     Jan
    -1.02
    June
    -0.99
     January
    -0.98
    POSITIVE LOGITS
     myſelf
    1.52
     Majefty
    1.43
     itſelf
    1.39
     houſe
    1.34
     pleaſure
    1.33
     Monfieur
    1.33
     purpoſe
    1.30
     raiſ
    1.30
    ſelves
    1.26
     themſelves
    1.24
    Activations Density 0.238%

    No Known Activations