© 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. 19293
    Prev
    Next
    INDEX
    Explanations

    keywords and constructs commonly associated with database operations and programming functions

    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
     […]
    -0.74
     disambiguazione
    -0.52
    documentElement
    -0.51
    […]
    -0.50
     defStyle
    -0.48
     [...]
    -0.44
     …
    -0.43
     Marcell
    -0.42
    entr
    -0.41
     zatem
    -0.41
    POSITIVE LOGITS
    Scénario
    0.71
     الحره
    0.68
     للمعارف
    0.64
    ecore
    0.64
    存于互联网档案馆
    0.62
     Offisielt
    0.62
    kkue
    0.61
    enoord
    0.61
    ->___
    0.60
     تضيفلها
    0.60
    Activations Density 0.072%

    No Known Activations