© 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. 15074
    Prev
    Next
    INDEX
    Explanations

    references to modeling and fashion-related concepts

    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
    Décès
    -0.81
    WireFormatLite
    -0.67
    FontOfSize
    -0.67
    =$?
    -0.65
    AndEndTag
    -0.60
     виправивши
    -0.57
    ArrowToggle
    -0.57
    ]));
    -0.56
    findpost
    -0.56
    Уважа
    -0.56
    POSITIVE LOGITS
    Beauty
    0.73
     Beauty
    0.69
     beauty
    0.63
     nakalista
    0.61
    model
    0.60
    beauty
    0.57
    模特
    0.57
     pageant
    0.57
    BEAUTY
    0.57
     BEAUTY
    0.55
    Activations Density 0.009%

    No Known Activations