© 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. 32369
    Prev
    Next
    INDEX
    Explanations

    references to physical violence and abuse

    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
    enoid
    -0.61
    DebuggerNonUser
    -0.59
    brink
    -0.57
    hésite
    -0.57
    licht
    -0.56
    ientôt
    -0.55
    hasMoreElements
    -0.54
    quicks
    -0.53
    kton
    -0.52
     Brant
    -0.52
    POSITIVE LOGITS
    bootstrapcdn
    0.79
     EconPapers
    0.75
     punches
    0.64
     punching
    0.61
    TestFixture
    0.59
     shoving
    0.59
    __.__
    0.57
     slapping
    0.57
     CommonModule
    0.54
     rattan
    0.53
    Activations Density 0.071%

    No Known Activations