© 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. 1-CLT-HP
    7. 14923
    Prev
    Next
    INDEX
    Explanations

    function

    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
     Great
    -0.50
     pesados
    -0.44
     M
    -0.43
     Re
    -0.43
     (
    -0.43
    ...
    -0.42
     re
    -0.41
    MutableLiveData
    -0.41
     &
    -0.41
     I
    -0.40
    POSITIVE LOGITS
     Monfieur
    0.98
     myſelf
    0.98
     itſelf
    0.95
     Shakspeare
    0.95
     fubject
    0.91
     Houſe
    0.90
     ſche
    0.89
     Reſ
    0.88
     houſe
    0.88
     faſt
    0.87
    Activations Density 0.006%

    No Known Activations