© 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. 21543
    Prev
    Next
    INDEX
    Explanations

    testimony related to operational safety and hazards in mechanical systems, particularly boilers

    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
    rungsseite
    -0.64
     ExecuteAsync
    -0.59
     محفوظة
    -0.55
    тивні
    -0.54
     SEDS
    -0.54
    Hochspringen
    -0.53
     antaranya
    -0.52
    folios
    -0.52
    }{#
    -0.52
     Caj
    -0.52
    POSITIVE LOGITS
     المعيارى
    0.61
    thenReturn
    0.57
    resizingMask
    0.57
    عداد
    0.52
    internalType
    0.51
    phosph
    0.50
     siste
    0.50
    PreAuthorize
    0.50
     lateinit
    0.50
     rež
    0.50
    Activations Density 0.192%

    No Known Activations