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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 1854
    Prev
    Next
    INDEX
    Explanations

    instances of 'example' and related phrases suggesting illustration or exemplification

    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
     CURLOPT
    -0.66
    وردار
    -0.66
    CURLOPT
    -0.64
    нование
    -0.64
    дожник
    -0.60
     requerimientos
    -0.59
     >=",
    -0.59
     lantaran
    -0.59
     StatefulWidget
    -0.58
    日在
    -0.58
    POSITIVE LOGITS
     examples
    1.87
     example
    1.72
    examples
    1.71
     Examples
    1.54
    example
    1.52
    Examples
    1.47
    Example
    1.42
     Beispiele
    1.42
     Example
    1.41
    exemple
    1.41
    Activations Density 0.373%

    No Known Activations