© 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. 10001
    Prev
    Next
    INDEX
    Explanations

    references to the Planck satellite and its analysis of cosmic microwave background data

    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
    Ivoire
    -0.66
     resourceCulture
    -0.56
    fwd
    -0.55
     Jaffe
    -0.55
    slu
    -0.53
    DUP
    -0.53
    ת
    -0.52
    dae
    -0.51
    setShow
    -0.50
    voire
    -0.50
    POSITIVE LOGITS
     Planck
    2.22
    Planck
    2.02
     CMB
    0.90
    annica
    0.88
     Plank
    0.85
    #+#
    0.78
    reportWebVitals
    0.77
     Efq
    0.76
    thral
    0.76
     Webber
    0.75
    Activations Density 0.005%

    No Known Activations