© 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. 24157
    Prev
    Next
    INDEX
    Explanations

    references to cosmological parameters and models

    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
    phylococcus
    -0.60
    Brin
    -0.60
    epiece
    -0.60
    حياته
    -0.58
    ждый
    -0.58
    咤
    -0.58
    çais
    -0.56
    ictwa
    -0.56
    Abp
    -0.56
    rgba
    -0.55
    POSITIVE LOGITS
     Cosmo
    1.30
     cosmological
    1.27
     cosmo
    1.24
    Cosmo
    1.18
     cosmology
    1.14
    cosmo
    1.04
     Heli
    0.84
    ^(@)
    0.84
     Cosmos
    0.83
     Cosmopolitan
    0.80
    Activations Density 0.002%

    No Known Activations