© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 590
    Prev
    Next
    INDEX
    Explanations

    the phrase "has been" and variations in different contexts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     fortfarande
    -1.13
     still
    -1.05
     ſtill
    -0.99
     ftill
    -0.98
    still
    -0.92
     itſelf
    -0.88
     likely
    -0.85
     fortsatt
    -0.83
     usually
    -0.79
     alſo
    -0.79
    POSITIVE LOGITS
     since
    0.68
     sejak
    0.66
     previously
    0.66
     through
    0.65
    ]='\
    0.64
     proven
    0.62
    CloseOperation
    0.62
     recently
    0.60
     recentemente
    0.60
     SINCE
    0.59
    Activations Density 0.186%

    No Known Activations