© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40136
    Prev
    Next
    INDEX
    Explanations

    je

    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
    #+#
    -0.64
     ma
    -0.58
     Ben
    -0.57
     AV
    -0.55
     ab
    -0.54
     F
    -0.52
     Tri
    -0.50
    ster
    -0.50
     Lim
    -0.48
     H
    -0.47
    POSITIVE LOGITS
     Monfieur
    1.08
     Efq
    1.07
     Theſe
    1.03
     purpoſe
    1.01
     ſeveral
    1.01
     myſelf
    1.01
     itſelf
    0.98
     themſelves
    0.96
     raiſ
    0.96
     ſtate
    0.95
    Activations Density 0.053%

    No Known Activations