© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19188
    Prev
    Next
    INDEX
    Explanations

    references to states of being emotionally or physically broken

    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
     itſelf
    -1.52
     myſelf
    -1.52
     himſelf
    -1.41
     themſelves
    -1.39
     againſt
    -1.38
     ſtate
    -1.35
     Efq
    -1.31
     purpoſe
    -1.30
     becauſe
    -1.27
     houſe
    -1.25
    POSITIVE LOGITS
     Broken
    0.85
    Broken
    0.82
     
    0.79
     broken
    0.77
    io
    0.76
     Bon
    0.73
    ness
    0.71
    broken
    0.68
    ar
    0.67
    ij
    0.67
    Activations Density 0.005%

    No Known Activations