© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 12232
    Prev
    Next
    INDEX
    Explanations

    concepts related to vision and visionary ideas

    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
    躇
    -0.91
     CMC
    -0.85
     Sae
    -0.81
     Plin
    -0.78
    adays
    -0.75
     Nal
    -0.75
     Collo
    -0.71
     ་་
    -0.71
    basicConfig
    -0.71
     Hels
    -0.71
    POSITIVE LOGITS
     Vision
    1.22
     VISION
    1.16
    Vision
    1.15
     vision
    1.10
    vision
    1.02
    VISION
    0.99
     Visions
    0.94
     visionary
    0.84
     visión
    0.80
     visions
    0.79
    Activations Density 0.004%

    No Known Activations