© 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. 16552
    Prev
    Next
    INDEX
    Explanations

    technical terms related to components and systems used in mechanical or electrical engineering

    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
     restantes
    -0.51
    CreateModel
    -0.49
     مناف
    -0.48
     anteriore
    -0.48
    gend
    -0.47
    ContextHolder
    -0.47
    complexType
    -0.47
    cheng
    -0.46
     diser
    -0.46
    зо
    -0.45
    POSITIVE LOGITS
     propOrder
    0.87
    anskje
    0.74
    PerformLayout
    0.74
    TintMode
    0.70
     <=",
    0.67
    ivasan
    0.67
    BASEPATH
    0.67
    לחה
    0.66
     समीक्षाओं
    0.64
    IntoConstraints
    0.64
    Activations Density 0.133%

    No Known Activations