© 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. 1825
    Prev
    Next
    INDEX
    Explanations

    the word "big" in various contexts, sometimes including related adjectives like "large" or superlatives like "great."

    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
    ReusableCell
    -0.75
     conditions
    -0.70
    MetaObject
    -0.61
     convertView
    -0.61
     Conditions
    -0.58
    SuppressLint
    -0.58
     Kondisi
    -0.58
    conditions
    -0.58
     approach
    -0.57
    Conditions
    -0.56
    POSITIVE LOGITS
     amounts
    1.07
    amounts
    0.93
     scale
    0.90
     quantities
    0.90
     amount
    0.87
     chunks
    0.83
     Amounts
    0.82
    amount
    0.79
    scale
    0.77
     sized
    0.77
    Activations Density 0.582%

    No Known Activations