© 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. 18-RES-MATRYOSHKA-DC
    7. 1607
    Prev
    Next
    INDEX
    Explanations

    mentions of wrongdoing and apologies.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    PullParser
    -0.65
     beginnetje
    -0.62
    
    -0.60
     Мексичка
    -0.58
    InSection
    -0.56
    atoare
    -0.56
    IsPostBack
    -0.55
    EDEFAULT
    -0.53
    stdc
    -0.52
     aspir
    -0.51
    POSITIVE LOGITS
     apology
    1.14
     investigation
    1.08
     apologized
    1.08
     exoner
    1.08
     apologised
    1.02
     apologizing
    1.00
     investigations
    0.98
     remorse
    0.96
     apologies
    0.94
     accusations
    0.93
    Activations Density 2.755%

    No Known Activations