© 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. 5689
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology related to integration and summation

    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
     Knochen
    -0.69
    scaler
    -0.68
    HasBeenSet
    -0.62
    DispatchToProps
    -0.60
    rrggbb
    -0.60
    UserScript
    -0.60
     cardinality
    -0.59
    nextProps
    -0.57
    ̣i
    -0.57
    ControllerAdvice
    -0.57
    POSITIVE LOGITS
    ∫
    0.81
     **)
    0.67
     integrals
    0.66
    Географиясе
    0.65
     bord
    0.64
    ORAGE
    0.61
    Портал
    0.60
    Посилання
    0.60
    breitung
    0.60
     uitge
    0.59
    Activations Density 0.059%

    No Known Activations