© 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. 10416
    Prev
    Next
    INDEX
    Explanations

    chemical elements and their symbols in 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
    Negative Logits
    RegistryLite
    -0.76
    SequentialGroup
    -0.71
     ostavi
    -0.68
    VersionUID
    -0.68
     الاطلاع
    -0.67
    >*/
    -0.65
     denture
    -0.64
     (;;
    -0.64
     Puck
    -0.63
    Portale
    -0.63
    POSITIVE LOGITS
    AsUp
    0.64
     running
    0.52
    CppMethod
    0.52
     StatelessWidget
    0.52
     corrid
    0.49
    ngdoc
    0.48
     Hor
    0.47
     henvisninger
    0.47
    ifel
    0.46
    راهيم
    0.46
    Activations Density 0.053%

    No Known Activations