© 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. 4-CLT-HP
    7. 395
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     estimés
    -0.59
    apimachinery
    -0.56
    BeginContext
    -0.54
    NewLabel
    -0.54
    \}^{
    -0.53
    SBATCH
    -0.53
     betweenstory
    -0.50
    Tembelea
    -0.50
    ubakar
    -0.49
    arote
    -0.49
    POSITIVE LOGITS
     purpoſe
    0.66
     ſtate
    0.66
     reaſon
    0.62
     Majefty
    0.58
     ſame
    0.58
    ...
    0.57
    I
    0.57
     Chriftian
    0.56
     ſmall
    0.56
     myſelf
    0.54
    Activations Density 0.016%

    No Known Activations