© 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. 5-CLT-HP
    7. 97419
    Prev
    Next
    INDEX
    Explanations

    import

    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
    englanniksi
    -0.57
    ấu
    -0.48
    níku
    -0.47
    chemy
    -0.47
    échelle
    -0.46
     سكانية
    -0.46
    ########.
    -0.46
     physically
    -0.45
    cemic
    -0.45
     Audiodateien
    -0.45
    POSITIVE LOGITS
    __);
    0.63
    Diwedd
    0.61
    ]--;
    0.54
    Portail
    0.52
    ]++;
    0.50
    ItemBackground
    0.50
    ecko
    0.50
    cipit
    0.47
     renouvel
    0.47
    enrollment
    0.45
    Activations Density 0.233%

    No Known Activations