© 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. 780
    Prev
    Next
    INDEX
    Explanations

    contrasting viewpoints

    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
    BagConstraints
    -0.66
    期刊论文
    -0.63
     архивлан
    -0.62
    makeConstraints
    -0.60
     Paglinawan
    -0.59
    qrstuvwxyz
    -0.57
    Portale
    -0.56
    digarh
    -0.54
    Chham
    -0.54
    zerland
    -0.53
    POSITIVE LOGITS
     Atem
    0.48
    Atsauces
    0.46
    曖昧さ回避
    0.46
     eccl
    0.46
    rungsseite
    0.45
     برانيه
    0.44
    Referencer
    0.43
     تانيه
    0.43
     tij
    0.42
    zeka
    0.42
    Activations Density 0.010%

    No Known Activations