© 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. 10916
    Prev
    Next
    INDEX
    Explanations

    references to medical study participants and their demographic characteristics

    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
     समीक्षक
    -0.70
    transQ
    -0.62
     الرياضيه
    -0.60
    Autoritní
    -0.59
    PerformLayout
    -0.56
    hysema
    -0.56
    RegressionTest
    -0.54
    hyrchwyd
    -0.54
    లాలు
    -0.52
     всего
    -0.52
    POSITIVE LOGITS
     createSlice
    0.62
     présidenti
    0.52
     fairer
    0.49
     présidentielle
    0.49
     getApp
    0.48
    éez
    0.47
    Aiheesta
    0.47
     chileno
    0.46
     voldo
    0.46
     terza
    0.45
    Activations Density 0.043%

    No Known Activations