© 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. 29282
    Prev
    Next
    INDEX
    Explanations

    probabilities associated with letter selection 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
    Negative Logits
    ↵↵↵
    -0.58
    __;
    -0.58
    ↵↵
    -0.57
    ↵
    -0.48
    ReusableCell
    -0.47
    fcntl
    -0.44
    ала
    -0.44
    ↵↵↵↵
    -0.42
    клопе
    -0.41
    σο
    -0.41
    POSITIVE LOGITS
    SharedCtor
    0.78
    AndEndTag
    0.78
    SourceChecksum
    0.78
    Personensuche
    0.74
    ammans
    0.69
    uestamente
    0.69
    ůměr
    0.68
    zsef
    0.68
     Pergamon
    0.68
    mphony
    0.66
    Activations Density 0.003%

    No Known Activations