© 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. 21556
    Prev
    Next
    INDEX
    Explanations

    numerical references and mathematical symbols in a technical context

    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
    mybatisplus
    -0.49
    će
    -0.47
     quoque
    -0.46
     onCancelled
    -0.45
     snack
    -0.44
     unit
    -0.44
     Años
    -0.44
    Hills
    -0.43
    reactivex
    -0.43
     AÑOS
    -0.43
    POSITIVE LOGITS
    ########.
    1.09
     nakalista
    0.90
     initComponents
    0.86
     Audiodateien
    0.86
     disambiguazione
    0.80
     للمعارف
    0.78
    adaptiveStyles
    0.73
    MigrationBuilder
    0.73
    rawDesc
    0.73
    Personensuche
    0.72
    Activations Density 0.227%

    No Known Activations