© 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. 92370
    Prev
    Next
    INDEX
    Explanations

    code or documentation

    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
    "])
    -1.00
    "]];
    -0.95
    "]}
    -0.95
     cherchés
    -0.90
    ()]);
    -0.90
    "]));
    -0.89
    ()");
    -0.88
    ]]=
    -0.87
    */;
    -0.87
    ."));
    -0.87
    POSITIVE LOGITS
    <bos>
    1.01
    '
    0.66
    ’
    0.59
     
    0.56
    y
    0.55
     n
    0.54
     I
    0.52
    ↵↵
    0.52
     of
    0.52
     to
    0.52
    Activations Density 0.133%

    No Known Activations