© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 3105
    Prev
    Next
    INDEX
    Explanations

    references to meta-analyses

    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
     met
    -1.13
     meet
    -1.05
     Meet
    -1.05
    Meet
    -1.02
    meet
    -1.00
     meeting
    -0.97
     meets
    -0.97
    Meeting
    -0.88
     Meeting
    -0.87
     Meets
    -0.83
    POSITIVE LOGITS
     meta
    2.86
    Meta
    2.67
     Meta
    2.63
    meta
    2.53
     META
    1.98
    META
    1.82
     méta
    1.74
     metaphysical
    1.23
     мета
    1.22
     metast
    1.19
    Activations Density 0.009%

    No Known Activations