© 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. 12-RES-MATRYOSHKA-DC
    7. 2842
    Prev
    Next
    INDEX
    Explanations

    references to final moments or conclusive events in a narrative

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    出版年
    -0.68
     EconPapers
    -0.58
    VersionUID
    -0.57
    appa
    -0.54
    lished
    -0.54
    INCREMENT
    -0.53
    ifiquement
    -0.53
    umenti
    -0.52
    AccessorTable
    -0.52
     mechanisms
    -0.51
    POSITIVE LOGITS
    remaining
    0.77
     Remaining
    0.75
     remaining
    0.73
     final
    0.71
    final
    0.71
    Final
    0.71
    Remaining
    0.70
     最后
    0.70
     FINAL
    0.66
    最後
    0.65
    Activations Density 0.171%

    No Known Activations