© 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. 20-CLT-HP
    7. 74703
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ſelf
    -0.85
     للاسماء
    -0.81
    )++;
    -0.80
    ſelves
    -0.69
    IActionResult
    -0.68
     Majefty
    -0.68
     }));
    -0.67
     myſelf
    -0.67
     الحره
    -0.66
    γχ
    -0.65
    POSITIVE LOGITS
    InitVars
    0.46
    kta
    0.43
     trực
    0.41
     propOrder
    0.40
     ostavi
    0.38
     réfrig
    0.38
    blat
    0.37
    rugada
    0.37
    bana
    0.37
     hujan
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.