© 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. 77192
    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
     Lordships
    -0.49
     Lindgren
    -0.49
     core
    -0.47
    玻
    -0.45
     cores
    -0.44
     Near
    -0.44
    نائ
    -0.43
     Ginn
    -0.43
     credit
    -0.43
     hot
    -0.43
    POSITIVE LOGITS
    EndContext
    0.65
    IntoConstraints
    0.63
    PRNewswire
    0.63
     EdgeInsets
    0.61
     @"/
    0.60
    ="@+
    0.60
     kasarigan
    0.59
    RTLD
    0.57
    下载附件
    0.56
     '{@
    0.56
    Activations Density 0.000%

    No Known Activations