© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5283
    Prev
    Next
    INDEX
    Explanations

    references to 'head' in various contexts, particularly in relation to headaches and medical terms

    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
     nahilalakip
    -0.78
    momix
    -0.71
     disponibilités
    -0.70
     Cricket
    -0.69
    solicit
    -0.67
    Allo
    -0.66
    rungsseite
    -0.66
     cricket
    -0.65
    acal
    -0.65
    ]]);
    -0.65
    POSITIVE LOGITS
     HEAD
    1.86
     heads
    1.80
     Heads
    1.73
     Head
    1.71
     head
    1.68
    Head
    1.68
    HEAD
    1.67
    heads
    1.63
    head
    1.61
    Heads
    1.57
    Activations Density 0.076%

    No Known Activations