© 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. 2-RES-MATRYOSHKA-DC
    7. 2754
    Prev
    Next
    INDEX
    Explanations

    references to protein inhibition, particularly involving the mitotic inhibitor protein

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagext
    -0.54
    lē
    -0.51
    όμε
    -0.49
     otr
    -0.47
    流水
    -0.47
    getOut
    -0.47
    beke
    -0.47
    Precis
    -0.47
    мак
    -0.47
    unas
    -0.46
    POSITIVE LOGITS
    mit
    3.25
     Mit
    3.22
     mit
    3.09
    Mit
    3.05
    MIT
    2.66
     MIT
    2.44
     mits
    1.84
    mitt
    1.79
    mits
    1.76
     Mitchell
    1.73
    Activations Density 0.027%

    No Known Activations