© 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. 3760
    Prev
    Next
    INDEX
    Explanations

    words related to a decrease or reduction

    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
    tritts
    -0.66
    πή
    -0.63
     aggiun
    -0.59
     Wadsworth
    -0.59
     popoli
    -0.59
     soste
    -0.58
    enoch
    -0.58
     commerciali
    -0.57
     Partially
    -0.56
     насељу
    -0.56
    POSITIVE LOGITS
     decline
    2.80
     Decline
    2.63
     declines
    2.55
    decline
    2.48
     declined
    2.47
    Decline
    2.44
     declining
    2.34
    decl
    1.84
     decl
    1.52
     refusal
    1.00
    Activations Density 0.013%

    No Known Activations