© 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. 239
    Prev
    Next
    INDEX
    Explanations

    lines of dialogue or direct quotations within a text

    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
    出版年
    -1.18
    دانشنامهٔ
    -1.09
     للمعارف
    -0.99
     BorderRadius
    -0.96
    发表于
    -0.95
     Houſe
    -0.94
    ]--;
    -0.93
    ItemBackground
    -0.93
    хьтан
    -0.93
    DeleteBehavior
    -0.92
    POSITIVE LOGITS
    :
    1.29
    ↵↵
    0.77
    ↵
    0.75
     :
    0.67
     suivante
    0.64
    ↵↵↵
    0.63
     
    0.62
      
    0.60
    ：
    0.60
    :
    0.59
    Activations Density 1.753%

    No Known Activations