© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 16243
    Prev
    Next
    INDEX
    Explanations

    phrases prompting imaginative thought or hypothetical scenarios

    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
     referenties
    -0.82
     StatefulWidget
    -0.78
    s
    -0.64
    bs
    -0.61
    geführt
    -0.58
    p
    -0.58
    sy
    -0.57
     Corbett
    -0.56
    ied
    -0.55
    tede
    -0.54
    POSITIVE LOGITS
     Imagination
    1.09
    Imagin
    1.07
     imagining
    1.02
    imagination
    0.99
     Imagine
    0.98
     Imagin
    0.98
     imagine
    0.95
     IMAG
    0.94
     imagin
    0.93
    imaginary
    0.93
    Activations Density 0.006%

    No Known Activations