© 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. 8010
    Prev
    Next
    INDEX
    Explanations

    patterns associated with web links or URLs, specifically from Twitter

    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
    Negative Logits
     betweenstory
    -0.75
    Hochspringen
    -0.73
    ISupport
    -0.70
    SequentialGroup
    -0.67
    OGND
    -0.63
    μως
    -0.63
    舺
    -0.63
     becauſe
    -0.62
    fromnode
    -0.62
    entrevista
    -0.62
    POSITIVE LOGITS
     typelib
    0.56
    AlterField
    0.52
    ezy
    0.45
    UTERS
    0.44
    SPATH
    0.44
    gnar
    0.40
    mpy
    0.39
    失礼
    0.39
    creativecommons
    0.39
     делу
    0.38
    Activations Density 0.049%

    No Known Activations