© 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. 21551
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations or physical structures within a specified area

    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
    extAlignment
    -0.73
    RenderAtEndOf
    -0.51
    ydı
    -0.50
    ielles
    -0.50
     EClass
    -0.49
    +#+
    -0.48
    SPJ
    -0.48
    keteers
    -0.48
     phải
    -0.47
    netinet
    -0.46
    POSITIVE LOGITS
     hindurch
    0.86
     through
    0.76
    through
    0.75
    Through
    0.71
    THROUGH
    0.69
     heen
    0.69
     Through
    0.66
    
    0.65
     attraverso
    0.61
     THROUGH
    0.60
    Activations Density 0.161%

    No Known Activations