© 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. 5-CLT-HP
    7. 92439
    Prev
    Next
    INDEX
    Explanations

    technical language

    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
     blessés
    -0.94
     périodes
    -0.93
     jambes
    -0.91
     fermés
    -0.91
     vérit
    -0.90
     écrits
    -0.87
     églises
    -0.85
     lèvres
    -0.85
     vœux
    -0.85
     travailleurs
    -0.85
    POSITIVE LOGITS
     utafitiHapana
    0.62
     MainAxisSize
    0.53
    });*/
    0.50
     kasarigan
    0.48
    <bos>
    0.48
    };*/
    0.47
     hemor
    0.45
    DoubleQuotes
    0.44
     sovere
    0.44
     concussion
    0.44
    Activations Density 0.016%

    No Known Activations