© 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. 286
    Prev
    Next
    INDEX
    Explanations

    XML or HTML tags and their corresponding closures within a structured format

    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
    حياته
    -0.47
     mutiny
    -0.47
    حياتها
    -0.45
    rückt
    -0.42
     Nadie
    -0.41
     monitors
    -0.41
     apartamento
    -0.41
    Kapp
    -0.41
     suivante
    -0.40
    hubungan
    -0.40
    POSITIVE LOGITS
     дописавши
    1.12
    RenderAtEndOf
    1.02
     insuffisamment
    1.00
    .*")]
    1.00
    
    1.00
     NSCoder
    0.94
    loài
    0.93
    ValueStyle
    0.90
    providedIn
    0.90
     endforeach
    0.88
    Activations Density 1.366%

    No Known Activations