© 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
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1442
    Prev
    Next
    INDEX
    Explanations

    uses of the word 'is' in various contexts, often followed by an adjective or noun phrase

    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
    StoryboardSegue
    -1.08
     EconPapers
    -0.89
     referenties
    -0.87
    InjectAttribute
    -0.80
    DockStyle
    -0.76
    
    -0.72
    WebElementEntity
    -0.70
    الدراسه
    -0.69
    prefixer
    -0.68
    Bioaccumulative
    -0.68
    POSITIVE LOGITS
     true
    1.10
     why
    1.10
    true
    1.03
    True
    0.93
     True
    0.88
     TRUE
    0.82
    why
    0.80
     waarom
    0.77
     because
    0.76
     happens
    0.74
    Activations Density 0.655%

    No Known Activations