© 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. 16684
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to case discussions

    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
     שוליים
    -0.81
     MainAxisSize
    -0.81
     disambiguazione
    -0.80
    
    -0.79
    sizeCache
    -0.78
    contentLoaded
    -0.76
     Huguen
    -0.72
    TargetException
    -0.71
    XmlAccessType
    -0.70
     kasarigan
    -0.69
    POSITIVE LOGITS
     Mr
    0.44
    pture
    0.42
    bov
    0.42
     لكرة
    0.41
     their
    0.41
     your
    0.40
     сами
    0.40
     dét
    0.40
     ấm
    0.40
     its
    0.40
    Activations Density 0.016%

    No Known Activations