© 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. 43211
    Prev
    Next
    INDEX
    Explanations

    contributes

    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
     contribute
    -1.20
     contributes
    -1.12
    Contributions
    -1.09
    Contributing
    -1.08
     contributing
    -1.05
     Contributing
    -1.05
     Contribute
    -1.04
     contributed
    -1.03
     contributions
    -1.02
     Contributions
    -1.01
    POSITIVE LOGITS
     to
    0.84
    rille
    0.62
     genocide
    0.61
     Dinah
    0.54
     coronation
    0.52
     Kamil
    0.52
     based
    0.51
     malice
    0.51
     money
    0.51
     best
    0.50
    Activations Density 0.160%

    No Known Activations