© 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. 20-CLT-HP
    7. 72932
    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
    WireFormatLite
    -0.61
     aren
    -0.61
     require
    -0.60
     weren
    -0.58
    клопе
    -0.56
    ChildScrollView
    -0.56
    complexContent
    -0.54
    HttpPut
    -0.52
    mybatisplus
    -0.51
     бъдат
    -0.51
    POSITIVE LOGITS
     suits
    0.60
    })));
    0.58
    }));
    0.57
     exists
    0.57
     signifies
    0.56
     initComponents
    0.56
     lies
    0.55
     matters
    0.54
     marks
    0.54
    usermodel
    0.52
    Activations Density 0.002%

    No Known Activations