© 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. 1-CLT-HP
    7. 12442
    Prev
    Next
    INDEX
    Explanations

    teen

    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
    teenth
    -1.34
     dump
    -0.90
     Dump
    -0.82
    })));
    -0.78
    PhysRevD
    -0.72
    ]--;
    -0.72
    Dump
    -0.70
    teen
    -0.70
     dumps
    -0.69
    ."));
    -0.68
    POSITIVE LOGITS
    ster
    0.61
    site
    0.50
    stad
    0.48
    span
    0.47
    はじめに
    0.47
    jarige
    0.46
    stra
    0.46
    side
    0.45
    stat
    0.45
    stats
    0.43
    Activations Density 0.043%

    No Known Activations