© 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. 29798
    Prev
    Next
    INDEX
    Explanations

    expressions of personal regret and reflection on past decisions

    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
    łosi
    -0.54
     impe
    -0.54
    GeneratedValue
    -0.50
    spre
    -0.48
     AssemblyCompany
    -0.48
    Tikang
    -0.47
     поможет
    -0.47
    GOTREF
    -0.46
    vincing
    -0.46
     счёт
    -0.45
    POSITIVE LOGITS
     GetEnumerator
    0.74
    RegistryLite
    0.63
    RenderAtEndOf
    0.63
     blessings
    0.57
    Benefits
    0.56
    曖昧さ回避
    0.56
     disadvantages
    0.55
     BENEFITS
    0.55
     simplifié
    0.55
    webElementXpaths
    0.54
    Activations Density 0.193%

    No Known Activations