Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 6327
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and terminology related to vector spaces and dimensions

    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
     SqlCommand
    -0.57
    TagHelper
    -0.56
    ScopeManager
    -0.55
     Permalink
    -0.53
     MotionEvent
    -0.53
     MonoBehaviour
    -0.51
    RenderAtEndOf
    -0.51
     offering
    -0.50
    thalam
    -0.50
    BaseAdapter
    -0.49
    POSITIVE LOGITS
     initComponents
    0.57
    Combine
    0.53
     Combine
    0.52
    ANNES
    0.52
     AssemblyCulture
    0.52
     combinar
    0.51
    Combined
    0.49
     ویکی
    0.49
    combination
    0.48
     combine
    0.47
    Activations Density 1.016%

    No Known Activations