© 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. 3679
    Prev
    Next
    INDEX
    Explanations

    references to the use of combination therapy

    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
     together
    -1.31
    together
    -1.21
    AndEndTag
    -1.19
     TOGETHER
    -1.18
    Together
    -1.16
     Together
    -1.13
    GETHER
    -0.96
     juntos
    -0.95
     juntas
    -0.94
    gether
    -0.90
    POSITIVE LOGITS
     combination
    2.25
    combination
    2.02
     Combination
    2.00
    Combination
    1.96
     combinations
    1.90
    combinations
    1.73
     Combinations
    1.63
     Kombination
    1.55
     combo
    1.50
     combinaison
    1.37
    Activations Density 0.009%

    No Known Activations