© 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. 28237
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals or events

    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
     Slow
    -0.62
    énario
    -0.61
    ãng
    -0.60
     întâ
    -0.59
     surla
    -0.56
     slow
    -0.55
    Slow
    -0.55
    ChildScrollView
    -0.55
     مرئيه
    -0.54
     étendue
    -0.54
    POSITIVE LOGITS
     aggressive
    0.75
     violent
    0.74
     fiery
    0.74
     brutal
    0.71
     ruthless
    0.70
     fierce
    0.69
     edgy
    0.69
     hars
    0.68
     forceful
    0.67
     violento
    0.67
    Activations Density 0.600%

    No Known Activations