© 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. 1-CLT-HP
    7. 11772
    Prev
    Next
    INDEX
    Explanations

    Jab

    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
    <bos>
    -0.94
    ValueStyle
    -0.86
     himſelf
    -0.71
     againſt
    -0.68
     themſelves
    -0.68
     ſeveral
    -0.66
     theſe
    -0.66
     ocasião
    -0.66
     cavalli
    -0.64
     Wicidata
    -0.63
    POSITIVE LOGITS
     Pei
    0.44
     poni
    0.44
    __':
    0.43
     Opens
    0.40
     Pem
    0.39
     Pontific
    0.39
    mitos
    0.38
     Keb
    0.38
    hand
    0.37
     palazzo
    0.37
    Activations Density 0.018%

    No Known Activations