© 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. 32479
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their components

    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
    Попис
    -0.82
    LookAnd
    -0.73
    erent
    -0.69
     AFR
    -0.68
    typeid
    -0.68
     Uhuru
    -0.68
    (&:
    -0.68
     Ogden
    -0.68
     Riet
    -0.68
     grains
    -0.67
    POSITIVE LOGITS
     DMSO
    1.76
    DMSO
    1.74
     Dime
    0.71
    ZZLE
    0.59
    mbra
    0.58
     Tamb
    0.58
     Tucker
    0.56
     Dowling
    0.56
     Distra
    0.56
    TabStop
    0.56
    Activations Density 0.002%

    No Known Activations