© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93196
    Prev
    Next
    INDEX
    Explanations

    activate

    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
     activating
    -1.95
    activate
    -1.94
     activation
    -1.88
    activating
    -1.84
    activated
    -1.82
     activate
    -1.81
     activated
    -1.78
     Activation
    -1.74
    activation
    -1.72
     Activated
    -1.70
    POSITIVE LOGITS
     Se
    0.65
     P
    0.56
     ap
    0.54
     Cor
    0.54
     C
    0.53
     Il
    0.52
     te
    0.51
     (
    0.51
     V
    0.51
     Al
    0.51
    Activations Density 0.550%

    No Known Activations