© 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. 15630
    Prev
    Next
    INDEX
    Explanations

    terms related to supersymmetry in theoretical physics

    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
    ustimmung
    -0.75
     createStore
    -0.74
    enumii
    -0.68
     snippetHide
    -0.66
    prnewswire
    -0.66
    ioutil
    -0.65
    phile
    -0.65
    classmethod
    -0.64
     mandatario
    -0.64
     Brodie
    -0.62
    POSITIVE LOGITS
     supers
    0.81
    ymmetry
    0.79
     SUS
    0.68
     Waw
    0.65
     Supers
    0.61
     Hadid
    0.60
     utafitiHapana
    0.59
    ymmetric
    0.53
    Supers
    0.52
     Normdatei
    0.51
    Activations Density 0.004%

    No Known Activations