© 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. 276
    Prev
    Next
    INDEX
    Explanations

    tabular data structures and numeric information within them

    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
    RUnlock
    -0.87
    yntaxException
    -0.66
     mergeFrom
    -0.66
    IsMutable
    -0.64
     peccato
    -0.63
    ğaz
    -0.60
     démission
    -0.59
    >//
    -0.58
     florales
    -0.58
    Rhestr
    -0.58
    POSITIVE LOGITS
     ومل
    0.56
     fieldNum
    0.55
     Pure
    0.52
    |^
    0.51
    aufs
    0.50
     Smart
    0.48
    ][]
    0.48
    abestanden
    0.48
     Kemp
    0.48
     &
    0.48
    Activations Density 1.231%

    No Known Activations