© 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. 14534
    Prev
    Next
    INDEX
    Explanations

    terms associated with scientific and mathematical concepts, particularly in the context of physical theories

    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
     doGet
    -0.47
     én
    -0.46
     micro
    -0.45
     ł
    -0.44
    orsese
    -0.44
     mini
    -0.44
    toHave
    -0.44
     كومونز
    -0.44
     ldc
    -0.43
    niaus
    -0.41
    POSITIVE LOGITS
    URLException
    0.84
     Theſe
    0.83
     paternity
    0.73
     photolibrary
    0.73
     Monfieur
    0.72
    mtrl
    0.69
     Beſ
    0.68
     ratification
    0.67
     Anſ
    0.67
    참고
    0.67
    Activations Density 0.004%

    No Known Activations