© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16201
    Prev
    Next
    INDEX
    Explanations

    SQL syntax elements and data type specifications

    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
    KommentareTeilen
    -0.84
     onCancelled
    -0.81
    TargetException
    -0.78
    NameInMap
    -0.72
    UnusedPrivate
    -0.65
    __':
    -0.61
     يتيمه
    -0.61
     initComponents
    -0.61
    __':
    -0.61
    AndEndTag
    -0.61
    POSITIVE LOGITS
    ंदीखरीदारी
    0.62
     appelez
    0.57
     ComVisible
    0.56
     développé
    0.53
     bogotá
    0.52
     النبات
    0.51
     décédé
    0.50
     caminando
    0.50
     Commissione
    0.48
    SHIP
    0.48
    Activations Density 0.059%

    No Known Activations