© 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. 5648
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with patents or technical specifications

    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
     nghiệm
    -0.48
     شب
    -0.45
     comen
    -0.45
    velo
    -0.43
     revised
    -0.43
    Verkehr
    -0.43
     الري
    -0.42
    atory
    -0.42
     Fal
    -0.41
     Gallen
    -0.41
    POSITIVE LOGITS
    Personendaten
    1.15
    SourceChecksum
    1.11
    aarrggbb
    1.10
     ویکی‌پدی
    1.10
     Roskov
    1.09
    NameInMap
    1.06
    بوابة
    0.99
    sizeCache
    0.98
    oredCriteria
    0.96
    parsedMessage
    0.94
    Activations Density 0.011%

    No Known Activations