© 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. 18-RES-MATRYOSHKA-DC
    7. 981
    Prev
    Next
    INDEX
    Explanations

    the start of sentences, especially conclusions in scientific papers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.84
     houſe
    -0.82
     itſelf
    -0.76
     myſelf
    -0.75
     pleaſure
    -0.73
     Houſe
    -0.72
    GOTREF
    -0.71
     Monfieur
    -0.71
     Majefty
    -0.69
     Efq
    -0.69
    POSITIVE LOGITS
     conclusion
    2.67
     Conclusion
    2.36
    conclusion
    2.33
    Conclusion
    2.28
     conclude
    2.25
     conclusions
    2.17
     conclusión
    2.16
     Conclusions
    2.11
    Conclusions
    2.08
     CONCLUSION
    2.06
    Activations Density 1.200%

    No Known Activations