© 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. 25931
    Prev
    Next
    INDEX
    Explanations

    references to cell death mechanisms in a scientific context

    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
     myſelf
    -0.83
     pleaſure
    -0.82
     ſever
    -0.74
     purpoſe
    -0.73
     juſ
    -0.71
     passim
    -0.70
    SBATCH
    -0.69
     pylint
    -0.69
    ędziesz
    -0.69
     ་་
    -0.69
    POSITIVE LOGITS
     
    0.53
     in
    0.49
    скан
    0.47
     our
    0.46
     interv
    0.44
    /
    0.43
     Human
    0.43
     humanas
    0.43
     n
    0.42
     story
    0.42
    Activations Density 0.189%

    No Known Activations