© 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. 16578
    Prev
    Next
    INDEX
    Explanations

    references to data generation and analysis in research

    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
     CreateTagHelper
    -0.78
     kasarigan
    -0.66
    })));
    -0.60
     ſub
    -0.60
    IntoConstraints
    -0.59
    таратура
    -0.59
    URLException
    -0.57
    MessageState
    -0.57
    Hentet
    -0.57
     Coton
    -0.57
    POSITIVE LOGITS
    enumii
    0.54
    gebnisse
    0.49
     event
    0.47
    InvalidProtocol
    0.47
    WTS
    0.47
    arResult
    0.46
    cipais
    0.46
    étaient
    0.45
     results
    0.45
    enumi
    0.45
    Activations Density 0.002%

    No Known Activations