© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 23386
    Prev
    Next
    INDEX
    Explanations

    emotional dialogue and expressions of remorse

    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
    Negative Logits
    RenderAtEndOf
    -0.64
    DeleteBehavior
    -0.54
    WriteBarrier
    -0.54
    tagHelperRunner
    -0.52
     صوتيه
    -0.52
    WillAppear
    -0.51
    MemoryWarning
    -0.49
     _$
    -0.47
     here
    -0.47
    #+#
    -0.46
    POSITIVE LOGITS
    ⓧ
    0.68
     Acknowledgments
    0.59
    ıyordu
    0.59
     Meksiku
    0.58
     betyd
    0.58
     Majefty
    0.58
    writeField
    0.57
     auffi
    0.57
     Récup
    0.57
     slat
    0.57
    Activations Density 0.933%

    No Known Activations